© 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. 46898
    Prev
    Next
    INDEX
    Explanations

    relates to applications and methods

    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
    çݲçıij
    -0.07
    ç´§æĢ¥
    -0.07
    èĭį
    -0.07
    è¿«
    -0.07
    ydd
    -0.06
     –
    -0.06
     representing
    -0.06
    inha
    -0.06
    ç©Ĺ
    -0.06
     عرض
    -0.06
    POSITIVE LOGITS
    LAY
    0.08
    azza
    0.08
    วà¹Īาย
    0.07
     espéc
    0.07
    bliche
    0.07
    ippets
    0.07
    å°½ãģı
    0.07
     PubMed
    0.07
    æĸ¹æĸ¹éĿ¢
    0.07
    æī§è¡Įèij£äºĭ
    0.07
    Activations Density 0.003%

    No Known Activations