© 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. 98694
    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
    ä¼ģ
    -0.25
    itant
    -0.25
    ocop
    -0.25
    飧
    -0.24
    elight
    -0.24
    Toe
    -0.24
    éĢļæĬ¥
    -0.24
     shutil
    -0.23
     Toe
    -0.23
    \Mail
    -0.23
    POSITIVE LOGITS
    EL
    0.26
     Bellev
    0.25
    çİ°åľº
    0.25
    åį¯
    0.25
    getField
    0.25
    orro
    0.24
    大åĨĽ
    0.24
    TES
    0.24
    ABEL
    0.24
    ES
    0.24
    Activations Density 0.251%

    No Known Activations

    This feature has no known activations.