© 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. 10051
    Prev
    Next
    INDEX
    Explanations

    categories and types

    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
     various
    -0.09
    缸åħ³çŁ¥è¯Ĩ
    -0.07
    ¥
    -0.07
    å¹³åı°å»ºè®¾
    -0.07
    æķ°éĩıåĴĮ
    -0.07
    缸åħ³è§Ħå®ļ
    -0.07
    _arrays
    -0.07
    å¦Īå¦Ī说
    -0.07
    人å±ħ
    -0.07
     numerous
    -0.07
    POSITIVE LOGITS
    -looking
    0.10
    ãĥĥãĤ°
    0.07
    æĪijæĿ¥è¯´ä¸¤åı¥
    0.07
    looking
    0.07
    åĴĮä¸Ģ个
    0.07
    gadas
    0.07
    ä¸įèĥ½åĨį
    0.07
    çĿĢçļĦ
    0.07
    stående
    0.07
    uffs
    0.06
    Activations Density 0.232%

    No Known Activations