© 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. 27366
    Prev
    Next
    INDEX
    Explanations

    responds to clinic

    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¸Ĭ涨äºĨ
    -0.07
    HLT
    -0.07
    åıĮèĬĤ
    -0.07
    æ»ĭæ»ĭ
    -0.07
    .dup
    -0.07
    izarre
    -0.07
     compounded
    -0.06
    ½ij
    -0.06
     Dup
    -0.06
     Wire
    -0.06
    POSITIVE LOGITS
    å¼ķ
    0.08
    å¤ļç§į
    0.08
     ÙĪجÙĩ
    0.07
    åħŃç§į
    0.07
     eligible
    0.07
    eligible
    0.07
    elig
    0.07
    èĮĥåĽ´åĨħ
    0.07
    以ä¸ĭåĩłç§į
    0.07
    æĬķãģĴ
    0.07
    Activations Density 0.006%

    No Known Activations