© 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. 44204
    Prev
    Next
    INDEX
    Explanations

    Changes and variations

    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
    åıĺåĮĸ
    -1.57
    çļĦåıĺåĮĸ
    -1.30
     changing
    -1.27
     changes
    -1.25
     change
    -1.25
    è®ĬåĮĸ
    -1.23
    åıĺåĬ¨
    -1.20
    åıĺ
    -1.18
     Change
    -1.16
    change
    -1.13
    POSITIVE LOGITS
    Cow
    0.25
    ewood
    0.25
    ÑĨев
    0.24
    -pagination
    0.23
     bầu
    0.23
    fov
    0.23
    éĶ±
    0.23
    à´Ł
    0.22
     cow
    0.22
    izzly
    0.22
    Activations Density 0.002%

    No Known Activations