© 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. 9341
    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
     merits
    -0.26
    /umd
    -0.25
    /fw
    -0.25
     illustration
    -0.25
    -den
    -0.24
    äºĶçĻ¾
    -0.24
     persisted
    -0.24
     guardian
    -0.24
    为ä¼ģä¸ļ
    -0.23
    -cn
    -0.23
    POSITIVE LOGITS
    rika
    0.29
    媳
    0.26
    ule
    0.26
    æħ¥
    0.25
    ritz
    0.25
    _ALWAYS
    0.25
    ulers
    0.25
    avel
    0.25
    æĹŃ
    0.25
    epam
    0.24
    Activations Density 0.228%

    No Known Activations

    This feature has no known activations.