© 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. 38497
    Prev
    Next
    INDEX
    Explanations

    about the

    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
    尼奥
    -0.09
    akedown
    -0.08
    æ·±æľī
    -0.08
    iaus
    -0.07
    isArray
    -0.07
    aup
    -0.07
    mans
    -0.07
    Frozen
    -0.07
    łíĮ
    -0.07
     ×ĸ×IJת
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    çļĦä¸įæĺ¯
    0.08
    èĥ½ä¸įèĥ½
    0.08
     mostly
    0.08
    ãģĤãģı
    0.08
     mainly
    0.08
    ä¸įåľ¨äºİ
    0.07
     gÅĤównie
    0.07
     getting
    0.07
    enna
    0.07
    Activations Density 0.081%

    No Known Activations