© 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. 32-TRANSCODER-HP
    7. 43360
    Prev
    Next
    INDEX
    Explanations

    wounds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endif
    -0.33
    _engine
    -0.28
     disp
    -0.28
     DISP
    -0.28
    ç»Ķ
    -0.27
     endif
    -0.27
    ENE
    -0.26
    offs
    -0.26
    iff
    -0.26
    涨
    -0.26
    POSITIVE LOGITS
     hemat
    0.29
    æĭĽåĭŁ
    0.25
    OURCE
    0.24
     Prospect
    0.24
    åľ¨å½ĵåľ°
    0.24
    chematic
    0.23
    éĤ£æł·çļĦ
    0.23
    å¤ļåľ°
    0.23
    ource
    0.23
     countryside
    0.23
    Activations Density 0.001%

    No Known Activations