© 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. 31-TRANSCODER-HP
    7. 18831
    Prev
    Next
    INDEX
    Explanations

    Various text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uly
    -0.30
    çļĦæ¨¡æł·
    -0.25
    å°ģ
    -0.25
    hog
    -0.24
    ate
    -0.24
    phem
    -0.24
     school
    -0.23
    Entered
    -0.23
    壯
    -0.23
    HEL
    -0.23
    POSITIVE LOGITS
    child
    0.34
     Child
    0.32
    æĸ¯åŁº
    0.29
    CHILD
    0.29
     child
    0.29
    VIN
    0.28
    Child
    0.28
    wnd
    0.28
    wk
    0.27
    lfw
    0.27
    Activations Density 0.882%

    No Known Activations