© 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. 38146
    Prev
    Next
    INDEX
    Explanations

    the following 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
     Palme
    -0.07
    reso
    -0.07
    orie
    -0.07
    viously
    -0.06
    IRQ
    -0.06
    mousemove
    -0.06
    ä¹ĭ为
    -0.06
    ueb
    -0.06
    ule
    -0.06
    èĩªä½ı
    -0.06
    POSITIVE LOGITS
     wording
    0.09
    å°±çŁ¥éģĵäºĨ
    0.08
    oblin
    0.07
     timing
    0.07
    æݪ
    0.07
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    0.07
     specifics
    0.07
     подÑĢобнее
    0.07
     implications
    0.07
     literature
    0.06
    Activations Density 0.039%

    No Known Activations