© 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. 4286
    Prev
    Next
    INDEX
    Explanations

    column names, numbers, code structures

    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
    驳
    -0.08
    zzi
    -0.08
    .Flat
    -0.07
    ä¹ĭå¤ľ
    -0.07
    owl
    -0.07
    ä»Ĭå¤ľ
    -0.07
    èĵĿåħī
    -0.07
    .removeListener
    -0.06
    acco
    -0.06
    yped
    -0.06
    POSITIVE LOGITS
     Biel
    0.08
    ç«¿
    0.07
    agog
    0.07
     numbered
    0.07
    çĴ§
    0.07
     Rú
    0.07
    multipart
    0.07
    æĭ§ç´§
    0.07
    åķ¦åķ¦
    0.07
    ä¸ĸåŃIJ
    0.07
    Activations Density 0.149%

    No Known Activations