© 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. 8221
    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
     Hang
    -0.28
    Hang
    -0.28
     ---
    -0.28
    æľ¯è¯Ń
    -0.27
    èµĦè´¨
    -0.26
     nhi
    -0.26
    èµĦæł¼
    -0.25
    universal
    -0.25
    ultipart
    -0.25
     Nhi
    -0.24
    POSITIVE LOGITS
    å²Į
    0.27
     naw
    0.27
     (~(
    0.25
    ç¬ı
    0.24
    ãĥ¼ãĥĹ
    0.24
    .every
    0.23
    ç±³ç²ī
    0.23
    alus
    0.23
    妯
    0.23
    oden
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.