© 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. 9493
    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
    Negative Logits
     cons
    -0.27
     genie
    -0.25
     preferred
    -0.24
     hesitation
    -0.24
    æľīä¿¡å¿ĥ
    -0.24
    inherit
    -0.24
    preferred
    -0.24
     Raq
    -0.23
    èĻij
    -0.23
    gate
    -0.23
    POSITIVE LOGITS
    ever
    0.29
    åħ¶ä½Ļ
    0.26
    _SCRIPT
    0.26
    ç»ĦæĪIJ
    0.24
     sequ
    0.24
    åİŁåĽłæĺ¯
    0.24
    Anth
    0.24
    åĬ³
    0.24
    继
    0.24
    tas
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.