© 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. 22287
    Prev
    Next
    INDEX
    Explanations

    came up with

    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
    两ä¸ī
    -0.07
    ä¸ĢçŃ¹
    -0.07
    ä»»ä½ķä¸Ģ个
    -0.07
    该æľīçļĦ
    -0.07
    antage
    -0.07
    åĿıäºĭ
    -0.07
    ä¸Ģ寸
    -0.06
    æĿ¥ä¹ĭ
    -0.06
    ä¸ĢåĪĨéĴ±
    -0.06
    ç¢į
    -0.06
    POSITIVE LOGITS
    äºĨä¸Ģå¥Ĺ
    0.12
    ä¸Ģå¥Ĺ
    0.10
    äºĨä¸Ģç³»åĪĹ
    0.09
    çļĦä¸Ģå¥Ĺ
    0.09
     devised
    0.08
    åıĪä¸Ģ
    0.08
    åIJį为
    0.08
     several
    0.08
    并äºİ
    0.07
    æĺ¯ä¸Ģå¥Ĺ
    0.07
    Activations Density 1.019%

    No Known Activations