© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39734
    Prev
    Next
    INDEX
    Explanations

    rotary instruments, syrup, state, fixation, masks, filter, uneven, sandwiches, conservative, protests

    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
    -quote
    -0.08
    кÑĤо
    -0.08
    _ABORT
    -0.07
    etch
    -0.07
    vid
    -0.07
    _ALLOW
    -0.07
    ster
    -0.07
    æ³ķç½ij
    -0.07
    ume
    -0.07
    ä¼ļåIJĮ
    -0.07
    POSITIVE LOGITS
    isser
    0.06
    æĹ©çĿ¡
    0.06
    ØŃÙĬ
    0.06
     optim
    0.06
    èİ
    0.06
    _tools
    0.06
    search
    0.06
    æłijä¸Ģ
    0.06
     reg
    0.06
    ä¸ī代
    0.06
    Activations Density 1.099%

    No Known Activations