© 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. 46373
    Prev
    Next
    INDEX
    Explanations

    example, e.g., consider, counterexample

    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
    æľīåı¯èĥ½ä¼ļ
    -0.08
    ereco
    -0.08
    agen
    -0.08
    çļĦä¸ĵæłı
    -0.08
    讲çļĦæĺ¯
    -0.08
     delimited
    -0.07
    æľīæŶåĢĻ
    -0.07
    oyer
    -0.07
     elsewhere
    -0.07
    æĢ»è§īå¾Ĺ
    -0.07
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.08
    èĢĥèĻij
    0.07
    ï¼ļ
    0.07
    è¢ĸ
    0.07
    èİ«è¿ĩäºİ
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.06
    æ¯Ķå¦Ĥ
    0.06
    åĮĢéĢŁ
    0.06
    kt
    0.06
    éĿłè¿ij
    0.06
    Activations Density 0.010%

    No Known Activations