© 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. 52846
    Prev
    Next
    INDEX
    Explanations

    divide

    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
    Not in Any Lists

    No Comments

    Negative Logits
     THEY
    -0.30
     они
    -0.29
    they
    -0.28
    “They
    -0.27
    They
    -0.27
    's
    -0.26
     they
    -0.26
    -FIRST
    -0.26
    ’s
    -0.25
     reactor
    -0.25
    POSITIVE LOGITS
     out
    0.43
     up
    0.40
     off
    0.36
     away
    0.34
     down
    0.34
    æİī
    0.31
    å¼ĢæĿ¥
    0.30
    æİīäºĨ
    0.29
     Up
    0.28
     apart
    0.28
    Activations Density 0.017%

    No Known Activations