© 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. 97588
    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
    EUR
    -0.24
    HAM
    -0.24
    çĸ¾
    -0.24
    idences
    -0.24
    ivirus
    -0.23
    ç½ij讯
    -0.23
    ropa
    -0.23
    ubyte
    -0.22
     EUR
    -0.22
    åĪ°
    -0.22
    POSITIVE LOGITS
    Arm
    0.29
    æĦı大
    0.28
    çĺ¾
    0.27
    æĸ¯åŁº
    0.27
     instrument
    0.27
     Instrument
    0.27
    .arm
    0.26
    å¾Īå·®
    0.26
     Arms
    0.25
    datum
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.