© 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. 38560
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    Negative Logits
     what
    -1.02
    what
    -0.85
     how
    -0.81
     What
    -0.73
    What
    -0.70
    .what
    -0.70
    å¦Ĥä½ķ
    -0.69
    ä»Ģä¹Īæĺ¯
    -0.69
    how
    -0.67
     why
    -0.66
    POSITIVE LOGITS
    æľįåĬ¡èĥ½åĬĽ
    0.26
    éĻħ
    0.25
    çļĦæ¯ĶèµĽ
    0.24
    èĢĮ对äºİ
    0.24
    anza
    0.24
    åĶ®
    0.24
    alement
    0.24
    edBy
    0.23
    鼶åĶ®
    0.23
    çļĦæľįåĬ¡
    0.23
    Activations Density 16.880%

    No Known Activations