© 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. 19-TRANSCODER-HP
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    Time and conditions

    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
    Negative Logits
     caster
    -0.30
    SS
    -0.27
    aire
    -0.27
    æ
    -0.26
    -<?
    -0.26
    ÑĥÑĩа
    -0.25
    In
    -0.24
    åĺĽ
    -0.24
    ä¸īåįģå¹´
    -0.24
     person
    -0.24
    POSITIVE LOGITS
    imers
    0.28
     sunk
    0.28
     tempted
    0.27
    ijken
    0.26
    utory
    0.25
    ollo
    0.25
    ensburg
    0.25
     unofficial
    0.25
    å¼Ģåħ³
    0.24
    stück
    0.24
    Activations Density 0.017%

    No Known Activations