© 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 EvalsExportsinterp-engineNEWAPI 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. 29036
    Prev
    Next
    INDEX
    Explanations

    website text

    np_max-act · gemini-2.0-flash

    tokens that are parts of web addresses or domain names (URL fragments and site-name pieces).

    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
    接手
    -0.08
    .gz
    -0.07
    represent
    -0.07
    auty
    -0.07
    Minus
    -0.07
    敏
    -0.07
     ADHD
    -0.07
     endian
    -0.07
    hw
    -0.07
     remar
    -0.06
    POSITIVE LOGITS
    ~/
    0.06
     çocukların
    0.06
    หมวด
    0.06
     đạo
    0.06
    目前国内
    0.06
    嗉
    0.06
    倘若
    0.06
     oportun
    0.06
    คำถาม
    0.06
    etary
    0.06
    Activations Density 0.062%

    No Known Activations