© 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. 112160
    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
    ajaran
    -0.28
    ritt
    -0.24
    iveau
    -0.24
    whether
    -0.24
    schools
    -0.24
     Planned
    -0.23
    .li
    -0.23
    lid
    -0.23
     alla
    -0.23
    ury
    -0.23
    POSITIVE LOGITS
    ãĢĮ
    0.25
    æĶ¾å¼ĥ
    0.24
    YZ
    0.23
    ark
    0.23
    M
    0.23
    %!
    0.23
    .Must
    0.23
    ce
    0.23
    lements
    0.23
    iju
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.