© 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. 35-TRANSCODER-HP
    7. 38902
    Prev
    Next
    INDEX
    Explanations

    -l

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laws
    -0.78
     legislation
    -0.72
     Laws
    -0.67
     legislative
    -0.66
    è§Ħå¾ĭ
    -0.66
    ç«ĭæ³ķ
    -0.64
     law
    -0.63
    laws
    -0.62
     Legislation
    -0.61
    law
    -0.59
    POSITIVE LOGITS
     зак
    0.37
    awy
    0.30
    ĭ
    0.29
    .aw
    0.28
    aw
    0.27
    gel
    0.25
    ĭè¯ķ
    0.25
     le
    0.24
    çļĦæľĢåIJİä¸Ģ
    0.24
    西äºļ
    0.24
    Activations Density 11.580%

    No Known Activations