© 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. 9593
    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
    人大
    -0.30
    åĪĩ
    -0.30
    ç½ijä¸Ĭ
    -0.27
    ata
    -0.26
    par
    -0.25
    äºĴ
    -0.25
     Safe
    -0.24
    é¢Ľ
    -0.24
    æĢ»ç®Ĺ
    -0.24
    ç½ijéĢļ
    -0.24
    POSITIVE LOGITS
    ardown
    0.28
    .hex
    0.28
    _but
    0.27
    ä½Ĩå¦Ĥæŀľ
    0.25
     NSS
    0.25
     converse
    0.25
    classify
    0.25
     fittings
    0.25
    berger
    0.24
    -functions
    0.24
    Activations Density 0.041%

    No Known Activations

    This feature has no known activations.