© 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. 41359
    Prev
    Next
    INDEX
    Explanations

    ending in "-al"

    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
     economically
    -0.39
     internally
    -0.38
    constitution
    -0.37
    emotion
    -0.37
     professionally
    -0.36
     medically
    -0.35
     genetically
    -0.35
     logically
    -0.35
    ically
    -0.34
     chem
    -0.34
    POSITIVE LOGITS
     mathematical
    0.60
     cultural
    0.59
     emotional
    0.57
     linguistic
    0.57
     musical
    0.56
     sexual
    0.55
     psychological
    0.55
     technological
    0.55
     architectural
    0.54
     spiritual
    0.52
    Activations Density 0.003%

    No Known Activations