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. 2828
    Prev
    Next
    INDEX
    Explanations

    algebra

    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
     Michaels
    -0.08
     Medicine
    -0.08
    _mock
    -0.07
    .Mock
    -0.07
     FLT
    -0.07
    _analysis
    -0.07
     después
    -0.06
     algún
    -0.06
    .getItem
    -0.06
    volución
    -0.06
    POSITIVE LOGITS
     //-
    0.06
    ;/*
    0.06
    ў
    0.06
     driveway
    0.06
    -window
    0.06
    ◈
    0.06
    荣耀
    0.06
     PROGRAM
    0.06
    &e
    0.06
     homes
    0.06
    Activations Density 0.003%

    No Known Activations