© 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. 9620
    Prev
    Next
    INDEX
    Explanations

    this is

    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¸ĢæĿ¡é¾Ļ
    -0.07
    getApplication
    -0.07
    าà¸ģล
    -0.07
     ÙĨد
    -0.07
    .ident
    -0.07
    å¦Ĥä½ķå¤ĦçIJĨ
    -0.07
    quer
    -0.07
    æīĢèĥ½åıĬ
    -0.06
    éĵģé¾Ļ
    -0.06
    ÙĤات
    -0.06
    POSITIVE LOGITS
    è¾ī
    0.09
    æij
    0.08
    deaux
    0.07
     disarm
    0.07
    ׳×Ļ
    0.07
    æŁ±
    0.07
    èĤ²
    0.06
    .annotations
    0.06
    ayne
    0.06
    èµŀ许
    0.06
    Activations Density 0.126%

    No Known Activations