© 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. 39012
    Prev
    Next
    INDEX
    Explanations

    sorting numbers and variables

    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
    çī¹æѤ
    -0.08
    hud
    -0.07
    èįŁ
    -0.07
    UED
    -0.07
    Caller
    -0.07
    åħ±
    -0.07
    ï¼ı
    -0.06
    æĹ¥æĹ¥
    -0.06
    ovah
    -0.06
    ilio
    -0.06
    POSITIVE LOGITS
    该款
    0.07
    ungal
    0.07
    idon
    0.07
     Parsons
    0.07
    inely
    0.07
    以太
    0.07
     complet
    0.06
     pala
    0.06
    FAULT
    0.06
    è¿Ļ个社ä¼ļ
    0.06
    Activations Density 0.003%

    No Known Activations