© 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. 42744
    Prev
    Next
    INDEX
    Explanations

    lists of items or clauses

    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
    echt
    -0.08
    Å¡Äį
    -0.07
    tat
    -0.06
    lade
    -0.06
    ocker
    -0.06
    ÙĨÙĩا
    -0.06
    ÙĨدÙĩ
    -0.06
    åĤħ
    -0.06
    æ£ł
    -0.06
    ñana
    -0.06
    POSITIVE LOGITS
    åĽłæŀľåħ³ç³»
    0.09
    éĹ´æİ¥
    0.09
     caul
    0.08
    oucher
    0.08
     vice
    0.08
     indirectly
    0.08
    å¯Ĩä¸įåı¯åĪĨ
    0.08
    åıįè¿ĩæĿ¥
    0.08
    uito
    0.08
    两èĢħ
    0.07
    Activations Density 0.390%

    No Known Activations