© 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. 65419
    Prev
    Next
    INDEX
    Explanations

    mouthfeel and description

    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
    å°±æľīåı¯èĥ½
    -0.09
    å°±åı¯èĥ½
    -0.07
    éĥ½åı¯èĥ½
    -0.07
    æľīåı¯èĥ½ä¼ļ
    -0.07
    æľīåı¯èĥ½
    -0.07
    aing
    -0.07
    ç»Ĩå¿ĥçļĦ
    -0.07
    åıĭ好çļĦ
    -0.07
    人ä¹ĭ
    -0.07
    ä¹Łæľīåı¯èĥ½
    -0.06
    POSITIVE LOGITS
    çļĦçī¹çĤ¹æĺ¯
    0.13
    çī¹çĤ¹æĺ¯
    0.13
    èĻ½è¯´
    0.10
    åIJĦæĸ¹éĿ¢
    0.10
    èĻ½æľī
    0.10
    èĻ½
    0.09
    åĨħ容丰å¯Į
    0.09
    ç»ĵæŀĦç®Ģåįķ
    0.09
    æĹłè®ºä»İ
    0.09
     برخ
    0.09
    Activations Density 0.100%

    No Known Activations