© 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. 25243
    Prev
    Next
    INDEX
    Explanations

    partition

    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
    ×Ļ×Ļ×Ŀ
    -0.08
    hoek
    -0.08
    çĻ¾éĩĮ
    -0.08
    celli
    -0.08
    ffel
    -0.08
    otin
    -0.07
    æ°¸ä¹ħæĢ§
    -0.07
    -setup
    -0.07
    åľ¨æľªæĿ¥çļĦ
    -0.07
    à¸Ĥัà¸Ļ
    -0.07
    POSITIVE LOGITS
     ordinal
    0.07
    åºı
    0.07
    erden
    0.06
    åĪĴåĪĨ为
    0.06
    æķ°çĽ®
    0.06
    fone
    0.06
    ç©·
    0.06
    recur
    0.06
    פשר
    0.06
    ULONG
    0.06
    Activations Density 0.008%

    No Known Activations