© 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. 9369
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Everyday
    -0.28
    гÑĥ
    -0.26
     intervention
    -0.26
    é¤
    -0.25
    emic
    -0.25
    oland
    -0.25
     createAction
    -0.25
    ofile
    -0.25
    soever
    -0.24
    管å±Ģ
    -0.24
    POSITIVE LOGITS
     wait
    0.29
    å¥ĩ
    0.28
     Wait
    0.28
    wait
    0.28
     WAIT
    0.27
    odka
    0.27
    (wait
    0.27
     waited
    0.26
    åĿĽ
    0.26
    _wait
    0.24
    Activations Density 1.238%

    No Known Activations

    This feature has no known activations.