© 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. 58109
    Prev
    Next
    INDEX
    Explanations

    figure or table identifiers

    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
    iband
    -0.07
    بÙĪد
    -0.07
     regen
    -0.07
    å½Ĵäºİ
    -0.07
     Ãļl
    -0.07
     Aviv
    -0.06
    ensem
    -0.06
    çĨł
    -0.06
    æľīçļĦæĺ¯
    -0.06
    ×Ľ×ª
    -0.06
    POSITIVE LOGITS
    ÙĪرة
    0.07
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    0.07
    ouncing
    0.07
    edig
    0.07
    jedn
    0.07
    anan
    0.07
    oppi
    0.06
    alani
    0.06
    inus
    0.06
    ãģĬæīĭ
    0.06
    Activations Density 0.048%

    No Known Activations