Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59457
    Prev
    Next
    INDEX
    Explanations

    accidents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dependence
    -0.08
     вы
    -0.08
     النهائي
    -0.07
    有幸
    -0.07
     Вы
    -0.07
     seeker
    -0.07
    인데
    -0.07
     است
    -0.06
     준비
    -0.06
    .Gravity
    -0.06
    POSITIVE LOGITS
    usive
    0.07
    윔
    0.07
    obl
    0.07
     Sands
    0.07
    スマ
    0.07
    ksen
    0.07
     חברת
    0.07
    ccak
    0.07
    (fm
    0.07
    欢乐
    0.07
    Activations Density 0.086%

    No Known Activations