© 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. 23774
    Prev
    Next
    INDEX
    Explanations

    latex math syntax

    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
    optic
    -0.08
    anto
    -0.07
    çĶ¨ä»¥
    -0.07
    estream
    -0.07
    æĺ¯çĶ¨æĿ¥
    -0.07
    èī³éĺ³
    -0.07
    æĹłæŀģ
    -0.07
    çĶ¨æĿ¥
    -0.07
    Substring
    -0.07
    rossover
    -0.07
    POSITIVE LOGITS
    ä¸Ģè·ĥ
    0.07
    icont
    0.07
    iat
    0.07
    à©Ģ
    0.07
    è¾Ľåĭ¤çļĦ
    0.07
     urat
    0.06
    æģ©
    0.06
    ä¸įè¦ģåİ»
    0.06
    ©
    0.06
    çłĶ
    0.06
    Activations Density 0.022%

    No Known Activations