© 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. 15644
    Prev
    Next
    INDEX
    Explanations

    $ ) } is divisible rational

    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
    äºİæѤ
    -0.08
    tero
    -0.08
     wer
    -0.08
     sid
    -0.07
     terc
    -0.07
    è¿ĺåĮħæĭ¬
    -0.07
    èĢĮ建
    -0.07
    loch
    -0.07
    uly
    -0.07
    esome
    -0.07
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.08
     Donovan
    0.07
    åĢĺ
    0.07
    ä¸Ģ个æĸ°çļĦ
    0.07
    Verifier
    0.06
    ä¹Łåħ·æľī
    0.06
    亦çĦ¶
    0.06
    婦
    0.06
     multis
    0.06
    UD
    0.06
    Activations Density 0.012%

    No Known Activations