© 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. 8039
    Prev
    Next
    INDEX
    Explanations

    our culture and society

    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
    ASAN
    -0.08
    æĦŁæĥħçļĦ
    -0.07
     {!!
    -0.07
    TTg
    -0.07
    ä¿ĿæĬ¤ä½ľçĶ¨
    -0.07
    stw
    -0.07
    kini
    -0.07
    ä¹ĭæŃ»
    -0.07
    ESTA
    -0.07
    ãģij
    -0.06
    POSITIVE LOGITS
     underlying
    0.09
    umbo
    0.08
    opus
    0.07
    obbies
    0.07
    bro
    0.07
    ongo
    0.07
    orsa
    0.07
     evolving
    0.07
    wit
    0.07
    ors
    0.06
    Activations Density 0.065%

    No Known Activations