© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    measurements and changes

    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
     sor
    -0.07
    unami
    -0.07
    ãģĮãģ¤
    -0.06
     (++
    -0.06
    brig
    -0.06
    etid
    -0.06
    족
    -0.06
    纬
    -0.06
     Sor
    -0.06
    Sor
    -0.06
    POSITIVE LOGITS
    ä¿¡æģ¯è¿Ľè¡Į
    0.09
    综åIJĪåĪĨæŀIJ
    0.08
     observed
    0.08
    æĪĸåĪ©çĶ¨
    0.07
    zeh
    0.07
    anch
    0.07
    éļ¾æĺĵ
    0.07
    å°±çŁ¥éģĵäºĨ
    0.07
    æ±łä¸Ń
    0.07
    è®°å½ķä¸ĭæĿ¥
    0.07
    Activations Density 0.153%

    No Known Activations