© 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. 14357
    Prev
    Next
    INDEX
    Explanations

    circumference, cable, lit, cameras, citrus, equipped

    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
    anes
    -0.09
    ลัà¸ģษà¸ĵà¹Į
    -0.08
    çĭ©çĮİ
    -0.08
    /xhtml
    -0.08
    è¿ĩåī©
    -0.08
    anship
    -0.08
    åĪĨä¹ĭä¸Ģ
    -0.08
    åģ¥åº·ç½ij
    -0.07
    åĪĨä¹ĭ
    -0.07
    ä¸įè¿ĩä»ĸ
    -0.07
    POSITIVE LOGITS
    为ä»Ģä¹Ī
    0.08
    æĺ¯æĪijåĽ½
    0.07
    ï¼İ
    0.07
    æ´Ĵ
    0.07
    lo
    0.07
    éĢīçĶ¨
    0.06
    为åķ¥
    0.06
    为ä»Ģä¹Īä¼ļ
    0.06
    ï
    0.06
    ä¸ĭåĪĹ说æ³ķ
    0.06
    Activations Density 0.001%

    No Known Activations