© 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. 63482
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ;]/
    -0.25
     transformers
    -0.24
    Editors
    -0.24
    _SHADER
    -0.24
     (£
    -0.23
    addle
    -0.23
    elden
    -0.23
    ä¸ĭæ²ī
    -0.23
    _ram
    -0.23
    agrid
    -0.23
    POSITIVE LOGITS
    OURS
    0.28
    nosis
    0.26
    ä¹ł
    0.26
    é©¿
    0.26
    Encoded
    0.25
    éļı
    0.25
    æ´»åĬ¨ä¸Ń
    0.24
    UTO
    0.24
    ä»ĩ
    0.24
     lick
    0.24
    Activations Density 1.399%

    No Known Activations