© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    aka, also known as

    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
    icast
    -0.08
    =__
    -0.08
     *.*
    -0.08
    etlen
    -0.08
    ãĥĥãĤ±
    -0.08
    indered
    -0.07
    illin
    -0.07
    naan
    -0.07
    ettino
    -0.07
    èĢĥéªĮ
    -0.07
    POSITIVE LOGITS
    ä¹Łåı«
    0.09
    ä¹Łç§°
    0.09
    åıĪ称
    0.09
    aka
    0.09
    ä¹Łç§°ä¸º
    0.09
    åıĪ称为
    0.09
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.08
    ä¹Łè¢«ç§°ä¸º
    0.08
    ç®Ģ称
    0.07
    åıĪåIJį
    0.07
    Activations Density 0.372%

    No Known Activations