© 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. 16806
    Prev
    Next
    INDEX
    Explanations

    page history edits

    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
    åıijå°Ħ
    -0.08
    è¿ħ鼷ä¸ĭè½½
    -0.08
    éĶĢåĶ®ç»ıçIJĨ
    -0.08
    çĥŃéŨæłĩçŃ¾
    -0.08
    /graphql
    -0.08
    æĸ°éĹ»å®¢æĪ·ç«¯
    -0.07
    缸åħ³èµĦ讯
    -0.07
    éļĻ
    -0.07
     /*#__
    -0.07
    è§Ĩéķľ
    -0.07
    POSITIVE LOGITS
     wiki
    0.10
    wik
    0.09
     wik
    0.08
     page
    0.08
     Wiki
    0.08
     Wikimedia
    0.08
    页éĿ¢
    0.08
    itorial
    0.08
     edits
    0.07
     civ
    0.07
    Activations Density 0.382%

    No Known Activations