© 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. 20-TRANSCODER-HP
    7. 142758
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨįä¸Ģ次
    -0.31
     dil
    -0.29
    æĺ¯æĢİæł·
    -0.28
    æĺ¯å¦Ĥä½ķ
    -0.28
    åĬĽè¿ĺæĺ¯
    -0.26
    çļĦåľ°
    -0.26
     fac
    -0.25
    -ring
    -0.25
    äºĨä¸Ģéģį
    -0.25
    enco
    -0.25
    POSITIVE LOGITS
    uckland
    0.28
    @email
    0.25
    åĴ¬
    0.25
    åIJĥå¾Ĺ
    0.25
    ä¸įåIJĥ
    0.25
     offsetof
    0.23
    æ²ĥ
    0.23
     optimization
    0.23
    å°Ķ
    0.23
    ursal
    0.23
    Activations Density 9.472%

    No Known Activations

    This feature has no known activations.