© 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. 39396
    Prev
    Next
    INDEX
    Explanations

    substring operations

    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
    ë¡Ŀ
    -0.07
    ç¦Ħ
    -0.07
     Sahara
    -0.06
    çĽijèĢĥ
    -0.06
     unb
    -0.06
    çİ°ä»»
    -0.06
    è¡ĮåĬ¨çļĦ
    -0.06
    Ñģла
    -0.06
    妨害
    -0.06
    éĺ®
    -0.06
    POSITIVE LOGITS
     corresp
    0.08
    åİŁä½ĵ
    0.08
    èĪ
    0.08
    æ°ijéĹ´åĢŁè´·
    0.07
    ILT
    0.07
    æĬĢæľ¯çĽijçĿ£
    0.07
    ]+)/
    0.07
     conceptual
    0.07
    åķĨ
    0.07
    ее
    0.07
    Activations Density 0.096%

    No Known Activations