© 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. 42360
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical connections

    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
    emel
    -0.09
    èģĶåIJĪåĪĽå§ĭ人
    -0.08
    ilter
    -0.08
    ersp
    -0.08
    æĶ¿å§Ķ
    -0.07
    ÑĢеÑĤ
    -0.07
    ĻĤ
    -0.07
    精工
    -0.07
    obie
    -0.07
    ernals
    -0.07
    POSITIVE LOGITS
    åı¯çŁ¥
    0.07
    çŁ¥çļĦ
    0.07
    yo
    0.06
    .lift
    0.06
    éĢģæĪij
    0.06
    iki
    0.06
     educ
    0.06
     th
    0.06
    ä¹ĭæľ¬
    0.06
    箫
    0.06
    Activations Density 0.111%

    No Known Activations