© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and roots

    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
    麾
    -0.08
    лам
    -0.08
    åĨįè¿ĩ
    -0.08
    大åĸľ
    -0.07
    群
    -0.07
    纳æĸ¯
    -0.07
    addon
    -0.07
    airy
    -0.07
    红çģ«
    -0.07
    kie
    -0.07
    POSITIVE LOGITS
    rove
    0.07
    æĩ·
    0.06
    貿
    0.06
    ohan
    0.06
    .roles
    0.06
    -back
    0.06
     roles
    0.06
     priori
    0.06
     call
    0.06
    èĭ¥è¦ģ
    0.06
    Activations Density 0.001%

    No Known Activations