© 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. 112598
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     slur
    -0.27
    ibur
    -0.27
     $('[
    -0.27
    etten
    -0.27
     Alf
    -0.26
    avn
    -0.26
     slab
    -0.25
     slip
    -0.25
    [p
    -0.25
    abol
    -0.25
    POSITIVE LOGITS
    rosis
    0.28
    /OR
    0.27
    à¹Ģà¸Ĺศ
    0.26
    ower
    0.26
     Cour
    0.26
    orses
    0.26
     converse
    0.26
    çļĦéĤ£ç§į
    0.26
     amat
    0.26
    cour
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.