© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45576
    Prev
    Next
    INDEX
    Explanations

    two categories

    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
    代ãĤıãĤĬãģ«
    -0.09
    ç»ıæµİä¸İ
    -0.08
    ola
    -0.07
    å¾·åįİ
    -0.07
    ä¸ī家
    -0.07
    warts
    -0.07
     instead
    -0.07
    icher
    -0.07
    åijĬ
    -0.07
    OLA
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.16
    åIJİèĢħ
    0.14
    çļĦåĮºåĪ«
    0.12
    ãģĿãĤĮãģŀãĤĮ
    0.12
     alike
    0.12
    ä¹ĭåĪĨ
    0.12
    åIJĦæľī
    0.12
     respectively
    0.11
    åIJĦèĩª
    0.11
    åIJĦèĩªçļĦ
    0.11
    Activations Density 0.279%

    No Known Activations