© 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. 22519
    Prev
    Next
    INDEX
    Explanations

    code syntax or programming terms

    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
    lebn
    -0.07
     ХоÑĤ
    -0.07
    ifar
    -0.07
    اد
    -0.06
     '&#
    -0.06
    OMATIC
    -0.06
    idar
    -0.06
    amac
    -0.06
    IDD
    -0.06
    éĺ¶
    -0.06
    POSITIVE LOGITS
    åľ¨æľĢè¿ij
    0.07
    人æĥħ
    0.07
    -wide
    0.07
    -floating
    0.07
    kü
    0.06
    æķ°ä»¥
    0.06
    Clock
    0.06
    çļĦä½ł
    0.06
    GP
    0.06
     UNIX
    0.06
    Activations Density 0.002%

    No Known Activations