© 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. 33732
    Prev
    Next
    INDEX
    Explanations

    hello world

    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
    åŁºäºİ
    -0.07
    èĥİåĦ¿
    -0.07
    Tick
    -0.06
    éĢĿ
    -0.06
    æ³ķéŨ
    -0.06
     based
    -0.06
    å¢ŀçĶŁ
    -0.06
    .removeChild
    -0.06
     Based
    -0.06
     shred
    -0.06
    POSITIVE LOGITS
    绣çŃ¹åįıè°ĥ
    0.08
    产ä¸ļ转åŀĭåįĩ级
    0.07
    ëĥ¥
    0.07
    alitas
    0.07
    usul
    0.07
    人åĽŀå¤į
    0.07
    åIJįåī¯
    0.07
    itan
    0.07
    åIJĪ秣
    0.07
    argon
    0.07
    Activations Density 0.001%

    No Known Activations