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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111922
    Prev
    Next
    INDEX
    Explanations

    demographics and geography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anvas
    -0.27
    art
    -0.26
    artial
    -0.25
     competent
    -0.25
    bat
    -0.24
    ante
    -0.24
    mobile
    -0.24
    ance
    -0.24
    itra
    -0.24
    干货
    -0.23
    POSITIVE LOGITS
    itemid
    0.28
    |č↵
    0.27
    ught
    0.27
    wald
    0.27
    lox
    0.26
    nez
    0.26
    chers
    0.26
    verted
    0.26
    æ¼Ķ
    0.25
     MyBase
    0.24
    Activations Density 0.034%

    No Known Activations