© 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. 7317
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    é¡»
    -0.07
    ure
    -0.07
    Ń
    -0.07
     unbe
    -0.06
    èĦ
    -0.06
     koll
    -0.06
    å°Ħ
    -0.06
     dừa
    -0.06
    ä¹ı
    -0.06
    atus
    -0.06
    POSITIVE LOGITS
    воÑĢÑı
    0.08
     ÑıкобÑĭ
    0.08
    asion
    0.07
    aves
    0.07
    ç»ĵæŀľæĺ¯
    0.07
    å°ıåŁİ
    0.07
    uccess
    0.07
    Ñıн
    0.07
    Declaration
    0.07
    æĪijä»¬çĽ¸ä¿¡
    0.06
    Activations Density 0.018%

    No Known Activations