© 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. 16747
    Prev
    Next
    INDEX
    Explanations

    if a certain fileif the mousepad has other functionsif a POS terminal is formed

    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
    ebra
    -0.09
    zelf
    -0.09
    roud
    -0.09
    rent
    -0.08
    ÑĤÑĢ
    -0.08
    ValuePair
    -0.08
    ë§ĪìŀIJ
    -0.08
    åı¯æ¢¦
    -0.08
    /gcc
    -0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
    POSITIVE LOGITS
    s
    0.11
    ات
    0.10
    ãģĦãĤĭ
    0.10
     latter
    0.08
    als
    0.08
    æĪij们对
    0.08
    æĪij们æľī
    0.08
    ../../../
    0.08
    ÏĤ
    0.07
    schein
    0.07
    Activations Density 0.002%

    No Known Activations