© 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. 8424
    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
    ä¾µ
    -0.30
    ç²Ĵ
    -0.28
    Late
    -0.27
    é¢Ĺç²Ĵ
    -0.26
    åĪ°æľĢåIJİ
    -0.25
     dur
    -0.25
    溯æºIJ
    -0.25
    -Origin
    -0.24
     Late
    -0.24
    puty
    -0.24
    POSITIVE LOGITS
    ä¸įè¿ľ
    0.31
    åı¸
    0.30
     Snowden
    0.26
    ãģĬãģĭãģĴ
    0.25
    appy
    0.25
    寻常
    0.25
    æŃ¡è¿İ
    0.25
     Rudd
    0.25
    ÑĪин
    0.24
    为ä¸Ģä½ĵ
    0.24
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.