© 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. 56576
    Prev
    Next
    INDEX
    Explanations

    deutschen Sprache

    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
    atism
    -0.07
    resse
    -0.07
    å°±æĥ³
    -0.07
    ä¸ĢåĽŀ
    -0.07
    æ³ĵ
    -0.07
     Pue
    -0.07
    å¦Ĩ
    -0.07
    ìľ
    -0.06
    untut
    -0.06
    mia
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.08
    æīįæĺ¯
    0.08
    æīį对
    0.08
    å¤įåĪ¶æĪĸ
    0.08
    æĪĸèĢħ缴æİ¥
    0.08
    è¿Ļæīįæĺ¯
    0.08
    PointF
    0.07
    æĪĸåħ¶ä»ĸ
    0.07
    ä¹ĭç±»çļĦ
    0.07
    æĪĸåĪ©çĶ¨
    0.07
    Activations Density 0.020%

    No Known Activations