© 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. 33-TRANSCODER-HP
    7. 52681
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     acc
    -0.27
     Ro
    -0.27
    Ro
    -0.26
    ders
    -0.26
    .Fields
    -0.25
     tracks
    -0.25
     transmission
    -0.24
    ans
    -0.24
    mat
    -0.24
     sher
    -0.24
    POSITIVE LOGITS
    _tem
    0.27
    istring
    0.26
    ulse
    0.26
    unga
    0.26
     Vivo
    0.26
    fts
    0.26
    ilib
    0.26
    澡
    0.25
    CTYPE
    0.25
    achi
    0.25
    Activations Density 0.006%

    No Known Activations