© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112919
    Prev
    Next
    INDEX
    Explanations

    complete

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     Influ
    -0.24
    磨
    -0.24
     remotely
    -0.24
     slightly
    -0.24
    çµĤ
    -0.23
    related
    -0.23
    ruc
    -0.23
     Terr
    -0.23
     eventually
    -0.23
     terminated
    -0.22
    POSITIVE LOGITS
    ingly
    0.31
    bred
    0.27
    å¤Ł
    0.25
    éľĨ
    0.24
    ÃŁe
    0.24
     vé
    0.24
    esting
    0.24
     bursts
    0.23
    ercul
    0.23
    ;y
    0.23
    Activations Density 0.189%

    No Known Activations