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

    Neuronpedia

    APICircuit 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. 2527
    Prev
    Next
    INDEX
    Explanations

    for

    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
     FUNC
    -0.08
     Illegal
    -0.08
    欢呼
    -0.08
     Invoice
    -0.08
    Transactional
    -0.08
    (detail
    -0.07
    Equality
    -0.07
    .createQuery
    -0.07
    _bi
    -0.07
    ►
    -0.07
    POSITIVE LOGITS
    me
    0.07
    センター
    0.06
    avy
    0.06
    Face
    0.06
    Entr
    0.06
    靥
    0.06
     lower
    0.06
    記
    0.06
     PM
    0.06
    ODY
    0.06
    Activations Density 0.039%

    No Known Activations