© 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. 48023
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    æİ
    -0.07
    çĩ
    -0.06
    å·¥
    -0.06
    ä¸Ģéģĵ
    -0.06
    atron
    -0.06
    åĪļåĪļ
    -0.06
    ä¸ĢæĹ©
    -0.06
    èĬĤ
    -0.06
    å¥Ĺ
    -0.06
    被å¥Ĺ
    -0.06
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.09
    ç»ĻåĪ«äºº
    0.09
    çĨŁèĥ½
    0.09
    owl
    0.08
    æĪijæĿ¥è¯´
    0.08
    Å¡o
    0.08
    IGHL
    0.08
    à¸Ĺัà¸Ķ
    0.08
    Äįu
    0.08
    rnd
    0.07
    Activations Density 0.009%

    No Known Activations