© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    classification codes

    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
    çIJIJ
    -0.08
    ulo
    -0.07
    erna
    -0.07
    é£Łçī©ä¸Ńæ¯Ĵ
    -0.06
    æķĪ
    -0.06
    ulai
    -0.06
     ÑĢей
    -0.06
    obo
    -0.06
    lut
    -0.06
    .tm
    -0.06
    POSITIVE LOGITS
    大类
    0.09
    ATEGORY
    0.08
    ç±»çļĦ
    0.08
    _CODES
    0.08
    nbsp
    0.07
     маÑĪи
    0.07
    åѦæĬ¥
    0.07
     Viá»ħn
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
     klasse
    0.07
    Activations Density 0.025%

    No Known Activations