© 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. 20-TRANSCODER-HP
    7. 141318
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations

    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
     fet
    -0.30
    bö
    -0.30
    ä¹Łå¸ĮæľĽ
    -0.27
     ov
    -0.26
    ³³
    -0.25
    交
    -0.25
    åIJĪ
    -0.25
    ga
    -0.25
    æĪIJéķ¿ä¸º
    -0.24
    lä
    -0.24
    POSITIVE LOGITS
     {}.
    0.26
    éĩijåŃĹ
    0.24
     Tar
    0.24
    antine
    0.23
    izard
    0.23
    elon
    0.23
    hunter
    0.23
    жÑĥ
    0.23
    legation
    0.23
    .submit
    0.23
    Activations Density 42.020%

    No Known Activations