© 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. 40587
    Prev
    Next
    INDEX
    Explanations

    questions and FAQs

    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
    æĤ²åī§
    -0.07
    çĶ¨å¿ĥ
    -0.07
    ozy
    -0.07
    à¦¾à¦ľ
    -0.06
    Unload
    -0.06
    æķĽ
    -0.06
    ç»ĵæ¡Ī
    -0.06
    istro
    -0.06
    ames
    -0.06
    è¡£è¢ĸ
    -0.06
    POSITIVE LOGITS
    çĸijéĹ®
    0.17
     questions
    0.17
    çĸijéļ¾
    0.16
    questions
    0.15
     Fragen
    0.14
    æľīçĸijéĹ®
    0.14
    çĸijåķı
    0.14
     Questions
    0.14
    /questions
    0.14
     вопÑĢоÑģов
    0.13
    Activations Density 0.370%

    No Known Activations