© 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. 64218
    Prev
    Next
    INDEX
    Explanations

    goals and support

    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
    áĥĵáĥĶ
    -0.10
    heimer
    -0.09
    weichen
    -0.09
    éĩĩ纳çİĩ
    -0.09
    èIJ½åľ¨äºĨ
    -0.08
    é«ĺèĢĥæĪIJ绩
    -0.08
    ikov
    -0.08
    áŀ¶áŀĻ
    -0.08
    enko
    -0.08
    ellis
    -0.08
    POSITIVE LOGITS
    åĽ¢éĺŁåIJĪä½ľç²¾ç¥ŀ
    0.07
    å¤įä¹ł
    0.07
    0.07
    éĢļè¿ĩè¿Ļ次
    0.06
    æľ¬è¯¾
    0.06
    åIJĽå®ī
    0.06
    ä¹ĭæĥħ
    0.06
    éĹ´æİ¥
    0.06
    并
    0.06
    è´°
    0.06
    Activations Density 0.011%

    No Known Activations