© 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. 7902
    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
    eldo
    -0.25
    kel
    -0.25
    æī¶
    -0.25
    æ¨ĺ
    -0.24
    'utilisation
    -0.24
    __(
    -0.24
    åĬĽéĩı
    -0.23
    afen
    -0.23
    aha
    -0.23
    rone
    -0.23
    POSITIVE LOGITS
    Liverpool
    0.26
    建åħļ
    0.25
     Serg
    0.25
    åľ¨å¹¿å·ŀ
    0.25
    åħļçļĦåįģ
    0.25
     parch
    0.25
    èĽĶ
    0.25
     COLL
    0.25
     Burl
    0.24
    èĭ±æł¼
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.