© 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. 9172
    Prev
    Next
    INDEX
    Explanations

    acquisition protocols

    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
    ä¸ĢåĪĩçļĦ
    -0.07
    è¯Ńè¨ĢåĴĮ
    -0.06
    жеÑĤ
    -0.06
     ç§ģ
    -0.06
    .mit
    -0.06
    ertext
    -0.06
    æ³¢çī¹
    -0.06
    alj
    -0.06
    ilon
    -0.06
    æīģå¹³
    -0.06
    POSITIVE LOGITS
    ilateral
    0.09
    reif
    0.08
    ilater
    0.08
    leman
    0.08
    并ä¸į代表
    0.07
    æıļãģĴ
    0.07
     inilah
    0.07
    à¹Īาà¸ĩ
    0.07
    onde
    0.07
    ÑĢоид
    0.07
    Activations Density 0.072%

    No Known Activations