© 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. 40874
    Prev
    Next
    INDEX
    Explanations

    circles

    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
    bedo
    -0.29
     Jad
    -0.28
    US
    -0.27
    vais
    -0.26
    _DAT
    -0.26
     Vive
    -0.25
    aits
    -0.25
    itter
    -0.25
     modele
    -0.25
    湿
    -0.25
    POSITIVE LOGITS
     circles
    0.54
     circle
    0.51
     Circle
    0.45
    åľĪ
    0.45
    Circle
    0.45
     Circ
    0.43
    circ
    0.42
     hex
    0.40
    hex
    0.39
     rings
    0.39
    Activations Density 0.001%

    No Known Activations