© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14812
    Prev
    Next
    INDEX
    Explanations

    hints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trained
    -0.08
    #__
    -0.08
    å°½èĩªå·±
    -0.08
    å¹´èİ·
    -0.08
    æľ¬æĸĩéĵ¾æİ¥
    -0.08
    è¿Ļä¸ĢåĪĩ
    -0.08
    æľĢæĸ°æĽ´æĸ°
    -0.08
    entro
    -0.08
    ikian
    -0.08
    etr
    -0.07
    POSITIVE LOGITS
    Hint
    0.12
     Hint
    0.11
    hint
    0.11
     hint
    0.11
     hints
    0.10
    æıIJ示
    0.10
    ãĥĴãĥ³ãĥĪ
    0.09
    _hint
    0.09
     clues
    0.08
     clue
    0.08
    Activations Density 0.035%

    No Known Activations