© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 109612
    Prev
    Next
    INDEX
    Explanations

    Cooling food

    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
     maintain
    -0.07
     explaining
    -0.07
     nghi
    -0.07
     건
    -0.07
     Constantin
    -0.07
     sandwiches
    -0.07
     Однако
    -0.06
     insisting
    -0.06
    汴
    -0.06
    uan
    -0.06
    POSITIVE LOGITS
    cade
    0.07
    (back
    0.07
    weak
    0.07
    宝妈
    0.07
     marketer
    0.07
    贴心
    0.07
    зо
    0.07
    _imgs
    0.06
    在过去
    0.06
    _EMIT
    0.06
    Activations Density 0.018%

    No Known Activations