© 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. 52634
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
    ↵↵
    -0.31
    ç½ij
    -0.30
    \
    -0.29
     be
    -0.27
    mn
    -0.27
     st
    -0.27
    ,
    -0.26
    ↵
    -0.26
     net
    -0.26
     say
    -0.26
    POSITIVE LOGITS
    é¹ħ
    0.31
    :e
    0.29
    ðĿijĴ
    0.29
    hof
    0.28
    &e
    0.28
     earrings
    0.28
    ernes
    0.27
     eing
    0.27
    -e
    0.26
     eof
    0.26
    Activations Density 0.035%

    No Known Activations