© 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. 50548
    Prev
    Next
    INDEX
    Explanations

    finding optimal results

    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
    ä»»ä½ķ
    -0.08
    æıIJä¾Ľä»»ä½ķ
    -0.08
     any
    -0.07
     Pir
    -0.07
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    åĴĮåĽ¾çīĩ
    -0.07
    çļĦä»»ä½ķ
    -0.06
    ä»»ä½ķæŶåĢĻ
    -0.06
    éĢłçī©
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¾ç¤º
    0.12
    ç»ĵæŀľè¡¨æĺİ
    0.11
    ç»ĵæŀľä¸º
    0.10
    çłĶ究表æĺİ
    0.09
    åıijçİ°æľī
    0.09
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.09
    ç»ĵæŀľæĺ¯
    0.09
    à¸ŀà¸ļวà¹Īา
    0.09
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.09
    åıijçİ°åľ¨
    0.09
    Activations Density 0.016%

    No Known Activations