© 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. 18941
    Prev
    Next
    INDEX
    Explanations

    multiple select

    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
    лайн
    -0.09
    åįķæĸ¹
    -0.07
    kbd
    -0.07
    Ùĥات
    -0.07
    æ¯Ķæĸ¹
    -0.07
    ablish
    -0.07
    没帮åĬ©
    -0.07
     buatan
    -0.07
    remos
    -0.07
    istics
    -0.06
    POSITIVE LOGITS
    éĶ¦ç»£
    0.07
    enus
    0.07
    çļĦåı¯èĥ½
    0.07
    ä¸įå¼ĥ
    0.07
    _dash
    0.06
    广
    0.06
    .rawValue
    0.06
     nature
    0.06
    èĸĩèĸĩ
    0.06
    äh
    0.06
    Activations Density 0.001%

    No Known Activations