© 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. 28233
    Prev
    Next
    INDEX
    Explanations

    often useful or used

    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
    ommer
    -0.07
    åĬªåĬĽå¥ĭæĸĹ
    -0.07
    æĪijèĩªå·±
    -0.07
    èĩ¼
    -0.06
    åıªæľīèĩªå·±
    -0.06
    umbu
    -0.06
    stered
    -0.06
    Rép
    -0.06
    cré
    -0.06
    åīįè¿Ľ
    -0.06
    POSITIVE LOGITS
    çĶ¨æĿ¥
    0.14
    çĶ¨äºİ
    0.14
    çĶ¨æĸ¼
    0.12
    åı¯ä»¥çĶ¨æĿ¥
    0.11
    çļĦè¿IJçĶ¨
    0.11
    æĺ¯çĶ¨æĿ¥
    0.11
    çĶ¨åľ¨
    0.11
    Used
    0.11
     used
    0.11
    çĶ¨ä½ľ
    0.11
    Activations Density 0.411%

    No Known Activations