© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64431
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    tokens that are punctuation delimiters or markup/code brackets (parentheses, square/curly/angle brackets, template tags, and similar delimiter tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    その
    -0.07
     Geli
    -0.07
    Phys
    -0.07
    öz
    -0.07
    Considering
    -0.07
    obre
    -0.07
    audio
    -0.06
     mentioning
    -0.06
    ypi
    -0.06
    identification
    -0.06
    POSITIVE LOGITS
    ₫
    0.07
    coding
    0.07
    captcha
    0.06
     chạy
    0.06
     palm
    0.06
    焦虑
    0.06
    的成本
    0.06
    chod
    0.06
    ButtonText
    0.06
    -label
    0.06
    Activations Density 0.221%

    No Known Activations