© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23433
    Prev
    Next
    INDEX
    Explanations

    beginning or end of

    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
    Kamis
    -0.08
    ours
    -0.08
    allery
    -0.07
     ÑģобÑĸ
    -0.07
    ä»İæĪij
    -0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.07
    ä»İéĤ£
    -0.07
    InBackground
    -0.07
    åľ¨ä»ĬåIJİ
    -0.07
    reja
    -0.07
    POSITIVE LOGITS
    ener
    0.08
    ToEnd
    0.07
    igr
    0.07
    zinho
    0.07
    ening
    0.07
    onet
    0.07
    èģĮä¸ļçĶŁæ¶¯
    0.07
    eni
    0.07
    istir
    0.07
    enu
    0.07
    Activations Density 0.069%

    No Known Activations