© 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. 41943
    Prev
    Next
    INDEX
    Explanations

    Professional Singing

    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
     chain
    -0.31
     kite
    -0.30
    chain
    -0.30
    åŁ¤
    -0.29
    éĵ¾æĿ¡
    -0.29
     kms
    -0.29
    rack
    -0.29
    æŁ°
    -0.28
    éĻIJ
    -0.27
    kins
    -0.26
    POSITIVE LOGITS
    åijĹ
    0.30
    boxing
    0.29
     singing
    0.27
     Record
    0.26
     Below
    0.26
    anon
    0.26
     du
    0.26
    endregion
    0.26
    -record
    0.26
    è®°
    0.26
    Activations Density 0.012%

    No Known Activations