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. 7204
    Prev
    Next
    INDEX
    Explanations

    Sports teams

    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
    mod
    -0.09
    üb
    -0.07
    쎌
    -0.07
    ool
    -0.06
    VBoxLayout
    -0.06
     ymin
    -0.06
    licated
    -0.06
     weil
    -0.06
     al
    -0.06
    isel
    -0.06
    POSITIVE LOGITS
    佽
    0.07
    CreatedBy
    0.07
     Playoff
    0.07
    بريطانيا
    0.07
    национа
    0.07
     appréci
    0.07
    Returned
    0.07
    مقاط
    0.07
    ♀♀♀♀
    0.07
     Hardcore
    0.07
    Activations Density 0.027%

    No Known Activations