© 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. 32-TRANSCODER-HP
    7. 43873
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fills
    -0.29
    atab
    -0.28
    ites
    -0.27
    bucks
    -0.27
    gap
    -0.26
    ustom
    -0.26
    sat
    -0.26
    çĺ¾
    -0.25
     Whites
    -0.25
    åĴĮ个人
    -0.24
    POSITIVE LOGITS
    èĥŀ
    0.28
    社ä¼ļ主ä¹ī
    0.27
    æĺ¥è¿IJ
    0.27
    溴
    0.27
    Axes
    0.26
    éļ¾
    0.24
    ISTICS
    0.24
    æĶ¾å¤§
    0.24
    ↵↵
    0.24
     Ampl
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.