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. 88348
    Prev
    Next
    INDEX
    Explanations

    9

    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
    8
    -0.08
    _cate
    -0.08
    ㋯
    -0.07
     strain
    -0.07
     of
    -0.07
    整理
    -0.07
    *this
    -0.07
    特性
    -0.07
    振
    -0.07
    (dispatch
    -0.07
    POSITIVE LOGITS
     footer
    0.07
     mocked
    0.07
    脖子
    0.07
     revenues
    0.07
     accountant
    0.07
    APPED
    0.07
    akk
    0.07
    odont
    0.07
    도록
    0.07
    idot
    0.07
    Activations Density 0.028%

    No Known Activations