© 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. 25453
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    à¸Ķ
    -0.07
    δεÏĤ
    -0.07
    resents
    -0.07
    æģª
    -0.07
    oot
    -0.07
    schede
    -0.07
    ogos
    -0.07
    ات
    -0.07
    εÏĤ
    -0.07
    گراÙĨ
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.14
    æ¯Ķå¦Ĥ
    0.13
     ÐĿапÑĢимеÑĢ
    0.10
    ä¾ĭãģĪãģ°
    0.10
     напÑĢимеÑĢ
    0.10
    icularly
    0.09
     például
    0.09
     ìĺĪ를
    0.09
     Misalnya
    0.09
     napÅĻÃŃklad
    0.09
    Activations Density 0.253%

    No Known Activations