© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20834
    Prev
    Next
    INDEX
    Explanations

    code snippets or syntax

    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
    "https
    -0.07
    ugin
    -0.07
    orman
    -0.06
    reso
    -0.06
    iro
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    御åı²
    -0.06
    genes
    -0.06
    ţe
    -0.06
    ä½Ĩåĩ¡
    -0.06
    POSITIVE LOGITS
    å°Ĩä¼ļ
    0.09
    请è¾ĵåħ¥
    0.09
    \t
    0.08
    èĤĨ
    0.07
    çľĭè§ģäºĨ
    0.07
    .toUpperCase
    0.07
    æ£Ģæµĭç»ĵæŀľ
    0.07
    çĶŁæ°´
    0.07
    Debug
    0.07
    æ£ĢæŁ¥ç»ĵæŀľ
    0.07
    Activations Density 0.055%

    No Known Activations