© 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. 1253
    Prev
    Next
    INDEX
    Explanations

    consciously presents

    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
    ä»Ģä¹Ī
    -0.07
     hoge
    -0.06
    èݽ
    -0.06
    kho
    -0.06
    rosse
    -0.06
     eventualmente
    -0.06
    rea
    -0.06
    çļĦäºĨ
    -0.06
    è¡¥
    -0.06
    hl
    -0.06
    POSITIVE LOGITS
     specifically
    0.09
    åħ·ä½ĵæĿ¥è¯´
    0.09
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.08
    æĺ¯æĮĩåľ¨
    0.08
    wai
    0.08
    oris
    0.07
    Specific
    0.07
    åħ·ä½ĵåĪĨæŀIJ
    0.07
    ocas
    0.07
    specific
    0.07
    Activations Density 0.002%

    No Known Activations