© 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. 27-TRANSCODER-HP
    7. 7969
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abs
    -0.30
    ctions
    -0.26
    icot
    -0.26
    çľĭæĿ¥
    -0.26
    %@
    -0.25
     McMahon
    -0.24
     jointly
    -0.24
    ufig
    -0.24
     Rubin
    -0.24
     phoenix
    -0.24
    POSITIVE LOGITS
    ä¸Ģç«Ļ
    0.27
    çĸ²ãĤĮ
    0.25
    群ä½ĵ
    0.25
     transports
    0.24
    æĺ¯æĪijåĽ½
    0.24
    æĬķåħ¥ä½¿çĶ¨
    0.24
     kettle
    0.23
     transported
    0.23
    注æĺİæĿ¥æºIJ
    0.23
     unusual
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.