© 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. 14595
    Prev
    Next
    INDEX
    Explanations

    limited quantity or size

    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
    èĻ½çĦ¶æ²¡æľī
    -0.07
    çĭ¬
    -0.07
    æŀĹæµ·
    -0.07
    ä½Ĩæĺ¯æ²¡æľī
    -0.07
    çĭ¬åįł
    -0.07
    apl
    -0.07
    [:-
    -0.07
     Unsigned
    -0.06
    preferred
    -0.06
    annels
    -0.06
    POSITIVE LOGITS
     limited
    0.17
    æľīéĻIJçļĦ
    0.16
    ä¹Łä¸įå¤ļ
    0.15
    limited
    0.15
    寥寥
    0.15
    ä¸įå¤ļ
    0.14
    æķ°éĩıæľīéĻIJ
    0.14
    ä»ħéĻIJäºİ
    0.14
    æľīéĻIJ
    0.14
    ä»ħæľī
    0.14
    Activations Density 0.197%

    No Known Activations