© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63626
    Prev
    Next
    INDEX
    Explanations

    technical/programming topics

    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
    ijn
    -0.28
    ãĥ©ãĥ³ãĤŃãĥ³ãĤ°
    -0.27
     kre
    -0.26
    itized
    -0.25
    /full
    -0.25
    综åIJĪæ²»çIJĨ
    -0.24
    ired
    -0.23
    agem
    -0.23
    çªģçł´
    -0.23
    æĤ¼
    -0.23
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.32
    ä¹Łè¦ģ
    0.30
    ):-
    0.27
     Cottage
    0.27
     counterpart
    0.27
     similarly
    0.27
     ÑĤоже
    0.27
    éħĿ
    0.26
    佬
    0.26
    裤åŃIJ
    0.26
    Activations Density 58.460%

    No Known Activations