© 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. 52521
    Prev
    Next
    INDEX
    Explanations

    computer code/technical language

    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
     b
    -0.28
    èįĴ
    -0.27
     pointer
    -0.27
    榷
    -0.26
     she
    -0.26
    çݯ
    -0.26
     Debt
    -0.26
     rock
    -0.25
     far
    -0.25
     Rocky
    -0.25
    POSITIVE LOGITS
    ToDevice
    0.32
    CLR
    0.31
    peria
    0.30
    :host
    0.29
    æĻ°
    0.26
    ãģĵãģ¨ãģ«
    0.26
    ATYPE
    0.26
    ToPoint
    0.26
    furt
    0.26
    åħ¨æĹ¥
    0.25
    Activations Density 0.006%

    No Known Activations