© 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. 38746
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

    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
     gén
    -0.28
     rainbow
    -0.27
    帮åĬ©
    -0.26
     roaring
    -0.26
    æĴŃ
    -0.26
     sparkling
    -0.26
    åħģ许
    -0.25
    åĩºãģĻ
    -0.25
    幫åĬ©
    -0.25
    å¼ĢèĬ±
    -0.25
    POSITIVE LOGITS
     bar
    0.36
     p
    0.35
    bar
    0.31
    缴è¾ĸå¸Ĥ
    0.29
    /*----------------------------------------------------------------
    0.29
    (p
    0.28
    æĹıèĩªæ²»å·ŀ
    0.28
    .p
    0.27
     '{@
    0.27
     Yemen
    0.27
    Activations Density 7.373%

    No Known Activations