© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    show derivatives or proofs

    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
    ulton
    -0.08
    engl
    -0.08
    ISTR
    -0.08
    opard
    -0.08
    rox
    -0.08
    æĮ¤
    -0.08
     Vinc
    -0.08
    çĻ¾å·Ŀ
    -0.08
     ÙĪاÙĦÙħØŃ
    -0.08
    éķ¿åĪ¶
    -0.08
    POSITIVE LOGITS
    æ±Ĥ
    0.09
    æ±Ĥå®ŀ
    0.08
    è¨ĺ
    0.07
    è®°
    0.07
    æ¢ģ
    0.07
    ãģĽ
    0.07
    tim
    0.06
    MA
    0.06
    å·²çŁ¥
    0.06
    åħ¬åı¸
    0.06
    Activations Density 0.002%

    No Known Activations