© 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. 42911
    Prev
    Next
    INDEX
    Explanations

    labels and names

    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
     label
    -0.43
     tag
    -0.36
     keyword
    -0.35
    	label
    -0.33
    _label
    -0.33
     exponent
    -0.32
    label
    -0.32
     identifier
    -0.32
    (label
    -0.32
    .label
    -0.31
    POSITIVE LOGITS
     labels
    0.68
    labels
    0.66
     names
    0.64
     IDs
    0.60
    	labels
    0.59
     keys
    0.57
    names
    0.57
    (labels
    0.56
     ids
    0.56
    (ids
    0.56
    Activations Density 0.004%

    No Known Activations