© 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. 27-TRANSCODER-HP
    7. 57594
    Prev
    Next
    INDEX
    Explanations

    conclusion indicators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ments
    -0.28
    æĹłæĦı
    -0.26
     Herald
    -0.26
    <Pair
    -0.25
     figure
    -0.24
    ãģĹãģ¾ãģĦ
    -0.24
    epy
    -0.24
    tering
    -0.24
    igy
    -0.24
    cplusplus
    -0.24
    POSITIVE LOGITS
     concluded
    0.39
     conclude
    0.39
     concludes
    0.37
    ç»ĵ论
    0.33
     conclusion
    0.32
    å¾Ĺåĩº
    0.32
    åĽłä¸º
    0.30
    Conclusion
    0.29
    æıIJåĩºçļĦ
    0.29
     proposed
    0.27
    Activations Density 0.010%

    No Known Activations