© 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. 20-TRANSCODER-HP
    7. 64609
    Prev
    Next
    INDEX
    Explanations

    iva

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ypse
    -0.27
    arine
    -0.27
    oteca
    -0.27
     Sparks
    -0.26
    gorithm
    -0.26
    çļĦæĹ¥åŃIJ
    -0.26
    elijk
    -0.25
    ỡ
    -0.24
    æĹ¥åŃIJ
    -0.24
    igkeit
    -0.24
    POSITIVE LOGITS
    亢
    0.30
     face
    0.28
    ilig
    0.26
    's
    0.26
    Faces
    0.26
    ’s
    0.26
    icy
    0.25
    rell
    0.25
    #{@
    0.25
    Rel
    0.24
    Activations Density 4.241%

    No Known Activations