© 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. 41038
    Prev
    Next
    INDEX
    Explanations

    kingdom, colony

    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
    令
    -0.24
     trụ
    -0.24
    ceptive
    -0.24
    isman
    -0.24
    è¦ļãģĪ
    -0.24
    ндекÑģ
    -0.23
    enko
    -0.23
    ifter
    -0.23
    ç£ĭ
    -0.23
    ли
    -0.23
    POSITIVE LOGITS
     well
    0.37
     ruled
    0.36
     known
    0.33
     headed
    0.33
     wells
    0.30
    well
    0.29
    known
    0.28
    Known
    0.28
     WELL
    0.28
    åĨ²
    0.27
    Activations Density 0.003%

    No Known Activations