© 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. 32515
    Prev
    Next
    INDEX
    Explanations

    Two, sub, locate, tri, all

    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
    -0.07
    æĪIJçīĩ
    -0.06
     запаÑģ
    -0.06
    æľīåĩł
    -0.06
    aul
    -0.06
    eward
    -0.06
     <
    -0.06
    å¼Ģå¼ł
    -0.06
    ä¸Ģæ¡£
    -0.06
     paired
    -0.06
    POSITIVE LOGITS
    å¤ĸæİ¥
    0.09
    åķ¡
    0.08
    æ¹ĥ
    0.08
    奥æķ°
    0.08
    ثار
    0.08
    UTILITY
    0.08
    anio
    0.08
    édi
    0.08
    orta
    0.08
     oe
    0.08
    Activations Density 0.007%

    No Known Activations