© 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. 129354
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Supporting
    -0.23
     ebenfalls
    -0.23
    atan
    -0.23
    rieve
    -0.22
     TBD
    -0.22
     tiá»ĩn
    -0.22
    è§Ģå¯Ł
    -0.22
    [at
    -0.22
    äºĨ解ä¸Ģä¸ĭ
    -0.22
    rien
    -0.21
    POSITIVE LOGITS
     invol
    0.26
    éģĹ
    0.25
    bol
    0.25
     consec
    0.24
    cons
    0.23
    å½±
    0.23
     dens
    0.22
    MeshPro
    0.22
    .kode
    0.22
    ":{"
    0.22
    Activations Density 82.110%

    No Known Activations