© 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. 49166
    Prev
    Next
    INDEX
    Explanations

    real-time

    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
    aroo
    -0.07
    eros
    -0.07
    etni
    -0.07
    astr
    -0.07
    tvr
    -0.07
    eru
    -0.07
    arach
    -0.07
    лим
    -0.07
    eve
    -0.07
    æĸ°éĹ»è®°èĢħ
    -0.07
    POSITIVE LOGITS
     giam
    0.07
    çī©çIJĨ
    0.07
    çļĦçī©çIJĨ
    0.07
    ä½ĵ积
    0.07
    大
    0.07
     physical
    0.06
    è¶ħ大
    0.06
     volume
    0.06
    physical
    0.06
    å¤ļ人
    0.06
    Activations Density 0.001%

    No Known Activations