© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44062
    Prev
    Next
    INDEX
    Explanations

    Technical documentation snippets

    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
    Negative Logits
     observed
    -1.19
     found
    -0.98
    found
    -0.87
     Found
    -0.85
    Found
    -0.85
     detected
    -0.84
     discovered
    -0.81
    _found
    -0.77
    	found
    -0.76
     noticed
    -0.75
    POSITIVE LOGITS
    ANDLE
    0.28
    lectic
    0.27
    ibri
    0.26
    å²ij
    0.26
    AYOUT
    0.25
    gram
    0.24
    Outcome
    0.24
    湿
    0.23
    _TURN
    0.23
     bundled
    0.23
    Activations Density 0.001%

    No Known Activations