© 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. 31655
    Prev
    Next
    INDEX
    Explanations

    question or statement endings

    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
    witz
    -0.07
    ä¹ĭåĪĥ
    -0.07
    empa
    -0.07
    åıįåĢĴæĺ¯
    -0.07
    assy
    -0.07
     hin
    -0.07
    caled
    -0.07
    prot
    -0.07
    igno
    -0.07
    waan
    -0.07
    POSITIVE LOGITS
    æĶ¾å®½
    0.07
    imenta
    0.07
    æľīä¸Ģçķª
    0.07
    ä¸į欲
    0.07
    满å¿ĥ
    0.07
    odb
    0.06
    æıIJåĩºè¦ģæ±Ĥ
    0.06
    åIJijæĹ¥
    0.06
    ä¾Ŀçħ§
    0.06
    åĥıä½ł
    0.06
    Activations Density 0.016%

    No Known Activations