© 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. 17491
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    oin
    -0.06
     напÑĢа
    -0.06
    mars
    -0.06
    ingle
    -0.06
    çĿ¹
    -0.06
     Ro
    -0.06
    çļĦ大åĬĽ
    -0.06
    ato
    -0.06
    åĩ³
    -0.06
    .hex
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.09
    两ç§įæĸ¹å¼ı
    0.08
    affles
    0.08
    å§ĭèĩ³
    0.08
    æºIJ
    0.08
    ×ŀ×ķת
    0.08
    EMS
    0.07
    äf
    0.07
     ÙĪزÙĨ
    0.07
    åĬłæĿĥ
    0.07
    Activations Density 0.011%

    No Known Activations