© 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. 56131
    Prev
    Next
    INDEX
    Explanations

    neuropsychologia, technology, differences, economics

    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
    olson
    -0.08
    骨èĤī
    -0.07
    ossi
    -0.07
    åĩĨæŶ
    -0.07
    ç§Ģç¾İ
    -0.07
    aglia
    -0.06
    ë°°
    -0.06
    èĮ¶æ°´
    -0.06
     Roose
    -0.06
    æĮ½
    -0.06
    POSITIVE LOGITS
    elier
    0.08
     antal
    0.07
    counts
    0.07
    å¤ļ空
    0.07
    æĢ»æķ°çļĦ
    0.07
    çıĢ
    0.07
    _trait
    0.07
    :type
    0.07
    çĴŁ
    0.07
    ×ķר×ķת
    0.07
    Activations Density 0.004%

    No Known Activations