© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    precancerous lesions

    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
    clang
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.06
    ä¸Ģå¼ı
    -0.06
    åĨħç»ı
    -0.06
     SIMD
    -0.06
    _EV
    -0.06
    éģĵ人
    -0.06
    egli
    -0.06
    åľ¨éĺħ读
    -0.06
    gne
    -0.06
    POSITIVE LOGITS
    flix
    0.08
    çĶ©
    0.08
    ÑĥÑģ
    0.07
    æĺĮåİ¿
    0.07
    ico
    0.07
     diversion
    0.07
     tuyá»ĥn
    0.07
     billets
    0.07
    ivec
    0.07
    缩çŁŃ
    0.07
    Activations Density 1.032%

    No Known Activations