© 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. 24581
    Prev
    Next
    INDEX
    Explanations

    composite number

    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»ĸ說
    -0.07
    asuk
    -0.07
     sÃŃn
    -0.07
     wsp
    -0.07
    æ©¡
    -0.07
    æĸĹ
    -0.07
     tán
    -0.07
    .getC
    -0.07
    alon
    -0.07
    ocas
    -0.07
    POSITIVE LOGITS
     again
    0.09
     Again
    0.09
     taas
    0.07
    again
    0.07
    Again
    0.07
    wijk
    0.07
    åıĪåĪ°äºĨ
    0.07
     опÑıÑĤÑĮ
    0.07
    ffffffff
    0.06
    æ´ŀéĩĮ
    0.06
    Activations Density 0.019%

    No Known Activations