© 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. 19292
    Prev
    Next
    INDEX
    Explanations

    DIY, self-made, handmade

    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
    ycin
    -0.07
    æĹłçĹĽ
    -0.07
    remium
    -0.07
    æĬ½è±¡
    -0.07
    ropp
    -0.07
     ино
    -0.06
    äär
    -0.06
    isplay
    -0.06
    çĮ
    -0.06
    ÙİعÙİ
    -0.06
    POSITIVE LOGITS
    èĩªè¡Į
    0.18
    èĩªå·±åĬ¨æīĭ
    0.18
    åı¯ä»¥èĩªå·±
    0.18
     DIY
    0.17
    èĩªåĪĨãģ§
    0.16
    èĩªå·±åģļ
    0.15
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    0.15
    åı¯èĩªè¡Į
    0.15
    亲æīĭ
    0.15
    èĩªå»º
    0.15
    Activations Density 0.361%

    No Known Activations