© 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. 29618
    Prev
    Next
    INDEX
    Explanations

    exemption from

    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
    ä¸įå¦Ļ
    -0.09
    -même
    -0.08
    èĨľçĤİ
    -0.08
    ä¸įæģ¯
    -0.08
    äºķçĦ¶
    -0.08
     اÙĦتØŃتÙĬØ©
    -0.08
    lero
    -0.07
    ourcem
    -0.07
    банка
    -0.07
    ÙĬÙģÙĬØ©
    -0.07
    POSITIVE LOGITS
     khá»ıi
    0.10
    /disable
    0.09
    /dis
    0.08
    icycle
    0.07
    ä¹ĭåĪĹ
    0.07
     granted
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    able
    0.07
    éĥ¨åĪĨ
    0.07
    itory
    0.07
    Activations Density 0.013%

    No Known Activations