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

    Neuronpedia

    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. 30951
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    instructions requesting a summary or conversion of text into bullet points (i.e., commands to summarize/condense content).

    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
    ughter
    -0.07
     ter
    -0.07
     melodies
    -0.06
    끌
    -0.06
    老乡
    -0.06
    ,response
    -0.06
     cor
    -0.06
    secret
    -0.06
    榜首
    -0.06
    api
    -0.06
    POSITIVE LOGITS
    FML
    0.09
     landscaping
    0.08
    concept
    0.07
    アル
    0.07
    PCA
    0.07
    avn
    0.07
    懋
    0.07
     ")"
    0.07
    冶
    0.07
    imum
    0.06
    Activations Density 0.157%

    No Known Activations