© 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. 52723
    Prev
    Next
    INDEX
    Explanations

    Code snippets and documents

    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
    eren
    -0.30
    ñe
    -0.28
    ascade
    -0.26
    awns
    -0.26
     dec
    -0.26
    ï¸
    -0.25
    ropp
    -0.25
    ictionary
    -0.24
    éģĹ产
    -0.24
    werp
    -0.24
    POSITIVE LOGITS
    ä¸įèĩ³äºİ
    0.28
     Pens
    0.25
    tha
    0.24
    ika
    0.24
    urate
    0.24
     brides
    0.24
    è¨Ģ
    0.24
    ä¸Ģå®ļç¨ĭ度
    0.24
    ä¸ºçĽ®çļĦ
    0.23
     sind
    0.23
    Activations Density 0.002%

    No Known Activations