© 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. 88199
    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
    lingen
    -0.28
    ç¿ĺ
    -0.26
    åľ°éģĵ
    -0.26
    Anchor
    -0.25
    eer
    -0.25
     Sesso
    -0.25
     incons
    -0.24
     déc
    -0.24
    partials
    -0.24
    ULK
    -0.24
    POSITIVE LOGITS
     Even
    0.26
    lica
    0.26
    ERS
    0.26
     McCartney
    0.26
    apat
    0.26
    庵
    0.25
     Merlin
    0.25
    omba
    0.25
     MER
    0.24
    ard
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.