© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    སར displays

    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
    ¬ģ
    -0.07
    u
    -0.07
    opro
    -0.06
    åľ¨ä¿Ŀè¯ģ
    -0.06
    asz
    -0.06
    ier
    -0.06
    uum
    -0.06
    emie
    -0.06
    \Builder
    -0.05
     Hafen
    -0.05
    POSITIVE LOGITS
    æĮģä¹ĭ以
    0.08
    ä»Ĭ次
    0.08
    漩
    0.08
    иÑĤелÑĮно
    0.08
    пеÑĩаÑĤ
    0.07
    ewis
    0.07
    .tim
    0.07
    versions
    0.07
    å¼Ģå±ķ好
    0.07
     Ella
    0.07
    Activations Density 0.024%

    No Known Activations