© 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. 52755
    Prev
    Next
    INDEX
    Explanations

    fire

    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
    æĤ¨çļĦåŃ©åŃIJ
    -0.27
     recap
    -0.27
    agonal
    -0.27
    .Par
    -0.26
    prise
    -0.25
     agenda
    -0.25
    agnostic
    -0.24
    æģķ
    -0.24
     Rey
    -0.24
    Moon
    -0.23
    POSITIVE LOGITS
    maps
    0.27
    åĪĩæĸŃ
    0.25
    æĿ¯
    0.24
    ắn
    0.24
     medi
    0.23
    æ
    0.23
     ger
    0.23
    ierz
    0.23
    cie
    0.22
    èį£èĢĢ
    0.22
    Activations Density 0.010%

    No Known Activations