© 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. 43981
    Prev
    Next
    INDEX
    Explanations

    schools/universities

    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
     track
    -0.28
    ŀæĢ§
    -0.27
    onica
    -0.26
    vertise
    -0.26
    track
    -0.25
    Track
    -0.25
     Vet
    -0.25
    onda
    -0.25
    -track
    -0.24
    说åĩº
    -0.24
    POSITIVE LOGITS
    intendent
    0.29
     Trinity
    0.29
    åĮ¡
    0.27
    bü
    0.25
    _stand
    0.25
    ç²
    0.24
     sno
    0.24
    ISTICS
    0.24
    /rfc
    0.24
    dux
    0.24
    Activations Density 0.004%

    No Known Activations