© 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. 42304
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     field
    -0.55
     Field
    -0.48
    field
    -0.47
    Field
    -0.46
     fields
    -0.43
    (field
    -0.41
    åľº
    -0.41
    	field
    -0.40
    fields
    -0.40
    -field
    -0.40
    POSITIVE LOGITS
     industry
    0.91
     Industry
    0.83
    Industry
    0.82
    industry
    0.76
     indust
    0.69
    å·¥ä¸ļ
    0.66
    è¡Įä¸ļ
    0.65
     industries
    0.59
     industrial
    0.58
    è¡Įä¸ļçļĦ
    0.58
    Activations Density 0.002%

    No Known Activations