© 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. 129267
    Prev
    Next
    INDEX
    Explanations

    cited

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
    çī©
    -0.26
    åĮħ
    -0.26
     Mahmoud
    -0.25
    æĮī
    -0.24
    $body
    -0.23
     Currently
    -0.23
    æĮīçħ§
    -0.23
    çIJ¨
    -0.23
     tro
    -0.23
    éŀĺ
    -0.23
    POSITIVE LOGITS
    人å¿ĥ
    0.29
    æĪijçļĦå¿ĥ
    0.28
    cene
    0.27
    æĪijä¸Ģ缴
    0.26
    wij
    0.26
     hoog
    0.26
    æ¯ı个人çļĦ
    0.26
    enschaft
    0.26
    å¿ĥå¢ĥ
    0.25
    iniz
    0.25
    Activations Density 11.320%

    No Known Activations