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. 59596
    Prev
    Next
    INDEX
    Explanations

    crocheting

    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
     дорог
    -0.07
     tup
    -0.07
    年轻人
    -0.07
     בהתאם
    -0.07
    碌
    -0.07
     taxpayer
    -0.07
    忽然
    -0.07
     Buf
    -0.07
     Parents
    -0.07
    Ps
    -0.07
    POSITIVE LOGITS
    -equiv
    0.08
    (example
    0.07
    严格按照
    0.07
    [rand
    0.07
    قال
    0.07
    stdbool
    0.07
    _makeConstraints
    0.07
    prov
    0.07
    coords
    0.07
     الاول
    0.07
    Activations Density 0.002%

    No Known Activations