© 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. 42124
    Prev
    Next
    INDEX
    Explanations

    submitted dates

    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»Ģ
    -0.08
    æĬĬæīĢæľīçļĦ
    -0.07
    åľ¨ä¿Ŀè¯ģ
    -0.07
    åŁ¹
    -0.06
    ap
    -0.06
    ฯ
    -0.06
    æłĵ
    -0.06
    æĻĥ
    -0.06
    çĶ©
    -0.06
    çľĭä¸ĭ
    -0.06
    POSITIVE LOGITS
    纶
    0.10
    ÙĨÙĩ
    0.09
    lify
    0.08
    çŃīæĪij
    0.07
    	ROM
    0.07
    ¤íĥ
    0.07
    æīĢæĢĿ
    0.07
    åħįè´¹åľ¨çº¿
    0.07
    ç´¯çļĦ
    0.07
    ZION
    0.07
    Activations Density 0.025%

    No Known Activations