© 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. 16489
    Prev
    Next
    INDEX
    Explanations

    current contextual descriptions

    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
    mdi
    -0.08
    alz
    -0.08
    èįĨ
    -0.07
    ä¸İåħ±
    -0.07
    رÙĬج
    -0.07
    å¨ħ
    -0.07
    ÑĩÑĮ
    -0.07
    ä¸įæĺİçļĦ
    -0.07
    amani
    -0.07
    hazi
    -0.07
    POSITIVE LOGITS
     ones
    0.09
     counterparts
    0.08
    ureau
    0.07
    åIJĮ类产åĵģ
    0.06
     similarly
    0.06
     Celle
    0.06
    ä¸įä»ħåľ¨
    0.06
    ä¸įå¾ĹäºĨ
    0.06
    ush
    0.06
    ö
    0.06
    Activations Density 0.224%

    No Known Activations