© 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. 40858
    Prev
    Next
    INDEX
    Explanations

    Code/foreign language

    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
     Feinstein
    -0.28
    ä»ĬçĶŁ
    -0.27
    åī¿
    -0.26
     tầm
    -0.26
    åı¯è§Ĥ
    -0.25
    çĶ¸
    -0.25
     /*#__
    -0.24
     parentheses
    -0.24
    ldre
    -0.24
     rehab
    -0.24
    POSITIVE LOGITS
    sch
    0.32
     dr
    0.31
    ricks
    0.30
    .Gr
    0.30
    uran
    0.28
    GRA
    0.28
    rics
    0.27
    gr
    0.27
     Gr
    0.27
    Gr
    0.27
    Activations Density 0.008%

    No Known Activations