© 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. 12297
    Prev
    Next
    INDEX
    Explanations

    url paths and domains

    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
     beda
    -0.08
    濯
    -0.08
    è¿Ļä¸ľè¥¿
    -0.08
    /disable
    -0.08
    @js
    -0.07
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
     -:
    -0.07
    ].'
    -0.07
    ادÙħ
    -0.07
    è¿Ļä¸ªä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    å°ģç¥ŀ
    0.06
    èģĮ
    0.06
    Stars
    0.06
    ëįĶ
    0.06
    iesta
    0.06
    ëĤ
    0.06
    åı¥åı·
    0.06
    人以ä¸ĭ
    0.06
     arg
    0.06
    usercontent
    0.06
    Activations Density 0.189%

    No Known Activations