© 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. 23243
    Prev
    Next
    INDEX
    Explanations

    production and costs

    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
    æµıè§Īéĩı
    -0.08
    icka
    -0.08
    iscard
    -0.07
    صÙĪر
    -0.07
    igur
    -0.07
    arb
    -0.07
    ÙĬØ·
    -0.07
    igg
    -0.07
    _UNSUPPORTED
    -0.07
    ôn
    -0.07
    POSITIVE LOGITS
    æ¯ıç§į
    0.11
    è¿Ļ两ç§į
    0.09
    è¿Ļä¸īç§į
    0.08
    两ç§į
    0.08
     cost
    0.08
    计åĪĴçļĦ
    0.08
    两类
    0.08
    计åĪĴ
    0.07
     plan
    0.07
    ä¸īç§į
    0.07
    Activations Density 0.010%

    No Known Activations