© 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. 129172
    Prev
    Next
    INDEX
    Explanations

    Citations and formal language

    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
     unp
    -0.28
    XL
    -0.27
     faç
    -0.25
     bá»ķ
    -0.24
    olygon
    -0.24
     unearth
    -0.23
     exterior
    -0.23
     downhill
    -0.23
     اÙĦÙħÙħÙĦ
    -0.23
     FileType
    -0.23
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.26
    loom
    0.26
    ãģ£ãģ±
    0.26
    ivas
    0.25
     provinc
    0.25
    okane
    0.24
    lems
    0.24
     variety
    0.24
    bish
    0.24
    iva
    0.23
    Activations Density 0.001%

    No Known Activations