© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8326
    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
    cka
    -0.30
    oten
    -0.29
    éİ®
    -0.27
    ewise
    -0.26
     perk
    -0.26
    zens
    -0.26
    ä»»
    -0.26
    éĻ£
    -0.25
    ýt
    -0.24
    odka
    -0.24
    POSITIVE LOGITS
     sci
    0.26
    æī¯
    0.25
    oure
    0.25
     spraying
    0.25
     caller
    0.25
    æĸ°å½¢åĬ¿ä¸ĭ
    0.24
     callers
    0.23
    omics
    0.23
    æĬ¢éĻ©
    0.23
    åħĭæľį
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.