© 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. 19-TRANSCODER-HP
    7. 8391
    Prev
    Next
    INDEX
    Explanations

    Explanations and reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aul
    -0.28
     wrap
    -0.26
    нÑĭ
    -0.25
    æĻ®åıĬ
    -0.25
    iamo
    -0.24
    urator
    -0.24
    inces
    -0.23
    åįĪ
    -0.23
    _WRAP
    -0.23
     visible
    -0.23
    POSITIVE LOGITS
    fav
    0.28
    å°±çŁ¥éģĵ
    0.27
    _KIND
    0.25
     rall
    0.25
    éĢł
    0.24
    å°±æĥ³
    0.24
     afar
    0.24
    cia
    0.24
    å°±æĬĬ
    0.24
    ç§ijæĬĢåĽŃ
    0.24
    Activations Density 0.760%

    No Known Activations