© 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. 64561
    Prev
    Next
    INDEX
    Explanations

    Paragraphs

    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
    uggy
    -0.30
    ä¸įå¿ĺ
    -0.27
    ization
    -0.27
     Sach
    -0.27
    æľªæĿ¥çļĦ
    -0.27
    urve
    -0.25
    izations
    -0.25
    Õ±
    -0.24
     sober
    -0.24
    çĶ¸
    -0.24
    POSITIVE LOGITS
    åĦ¿
    0.32
    åħĴ
    0.28
    ILA
    0.27
    åħī
    0.27
    %'↵
    0.27
    endar
    0.27
    åĨ¬
    0.26
    rum
    0.26
    åŁºæľ¬
    0.26
    'A
    0.26
    Activations Density 25.409%

    No Known Activations