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. 72528
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    atisfied
    -0.08
    permanent
    -0.07
    Ə
    -0.07
    ,number
    -0.07
    PLACE
    -0.07
     cotton
    -0.07
    �
    -0.07
    _Sh
    -0.07
     POINT
    -0.07
    (Un
    -0.07
    POSITIVE LOGITS
    ена
    0.08
    eken
    0.08
    稳步
    0.07
    ительно
    0.07
     significantly
    0.07
    ечно
    0.07
    变得
    0.07
     hopefully
    0.07
     немного
    0.07
    なかなか
    0.07
    Activations Density 0.039%

    No Known Activations