© 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. 31296
    Prev
    Next
    INDEX
    Explanations

    drift

    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
    缸è¾ħ缸æĪIJ
    -0.09
    itario
    -0.08
    иÑĩ
    -0.08
    quiera
    -0.08
    ielo
    -0.08
    -sama
    -0.08
    OfDay
    -0.08
    ÙĪÙĬØ©
    -0.08
    onais
    -0.08
    itÃł
    -0.07
    POSITIVE LOGITS
    icult
    0.09
    ers
    0.08
    ợ
    0.07
    å·²ä¹ħçļĦ
    0.07
    ä¸ĭæĿ¥çļĦ
    0.07
    ëĿ½
    0.07
    uvi
    0.07
    avion
    0.07
    inging
    0.07
    age
    0.07
    Activations Density 0.003%

    No Known Activations