© 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. 13817
    Prev
    Next
    INDEX
    Explanations

    reference values and intervals

    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
     пÑĢогÑĢеÑģÑģи
    -0.08
    ä»®
    -0.08
    æ³¥
    -0.07
    æĥħåĨµåĪĨæŀIJ
    -0.07
    pens
    -0.07
     Presup
    -0.07
     cerdas
    -0.07
    illah
    -0.07
     ram
    -0.07
    /projects
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽæķ°æį®
    0.10
     compil
    0.10
     databases
    0.09
    idata
    0.09
     data
    0.08
    accur
    0.08
     accurate
    0.08
     measurements
    0.08
     values
    0.08
     tab
    0.08
    Activations Density 0.185%

    No Known Activations