© 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. 13968
    Prev
    Next
    INDEX
    Explanations

    uses a method or purpose

    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
    mani
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    راÙģÙĬØ©
    -0.06
    æľīä»»ä½ķ
    -0.06
    raries
    -0.06
    pee
    -0.06
    inda
    -0.06
    othy
    -0.06
    é¸¡æ¯Ľ
    -0.06
    .Arguments
    -0.06
    POSITIVE LOGITS
    æĬĢæľ¯æīĭ段
    0.10
    çĤ¹å¯¹
    0.08
    ä»ĸæĿ¥
    0.08
    äºĭå®ŀè¯ģæĺİ
    0.08
    çŃīæīĭ段
    0.08
    agl
    0.08
    ä¸Ģéģĵéģĵ
    0.08
    çļĦä¸Ģç³»åĪĹ
    0.08
    以ä¸ĭæĸ¹å¼ı
    0.07
    çļĦä¸įæĸŃ
    0.07
    Activations Density 0.021%

    No Known Activations