© 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. 44158
    Prev
    Next
    INDEX
    Explanations

    Drywall and construction

    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
     vess
    -0.29
    uant
    -0.26
    uite
    -0.25
    tones
    -0.25
    iation
    -0.25
     ar
    -0.25
    opus
    -0.25
    转åĮĸ
    -0.25
    adier
    -0.25
     bow
    -0.25
    POSITIVE LOGITS
    AGMA
    0.29
     ÑĢазвива
    0.28
     ld
    0.25
    å¥¹åľ¨
    0.24
    _ing
    0.24
    åĸ·
    0.24
    lds
    0.23
     Indies
    0.23
    stud
    0.23
    lag
    0.23
    Activations Density 0.002%

    No Known Activations