© 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. 87166
    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
     bil
    -0.31
    atel
    -0.26
    cast
    -0.26
    oram
    -0.26
    æĶĴ
    -0.25
    ografia
    -0.24
    ä¸Ģ个æľĪ
    -0.24
    orama
    -0.24
    åıªä¸įè¿ĩ
    -0.24
    RH
    -0.24
    POSITIVE LOGITS
    (mut
    0.25
     clearly
    0.25
    adier
    0.25
    haus
    0.24
    -direct
    0.24
    ’ll
    0.24
    .Dev
    0.24
    æĶ¾å¿ĥ
    0.23
    -device
    0.23
    _device
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.