© 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. 41259
    Prev
    Next
    INDEX
    Explanations

    compose music

    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
    èĸĦ
    -0.37
    æĭĮ
    -0.32
    panel
    -0.29
     panel
    -0.26
    æŀ¶
    -0.26
    -runner
    -0.25
    çļĦæĦıæĢĿ
    -0.25
     Panel
    -0.25
    opard
    -0.25
     panels
    -0.25
    POSITIVE LOGITS
     compose
    0.51
    compose
    0.46
     composition
    0.44
    composition
    0.42
     composed
    0.42
    Compose
    0.42
     Composition
    0.41
    Composition
    0.40
     compositions
    0.39
     composing
    0.39
    Activations Density 0.003%

    No Known Activations