© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48198
    Prev
    Next
    INDEX
    Explanations

    mathematical estimation and derivation

    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
    æīĵ人
    -0.07
    irro
    -0.07
    à¹Ģà¸ķิ
    -0.07
    quine
    -0.06
    gles
    -0.06
     Cheer
    -0.06
     Alco
    -0.06
    à¹Ģศษ
    -0.06
    æīĵæĿ¥
    -0.06
    _RAM
    -0.06
    POSITIVE LOGITS
    估计
    0.08
    cov
    0.08
    å½Į
    0.08
    teg
    0.08
    Singleton
    0.08
    æĻ´
    0.07
     estimator
    0.07
    å¼¥
    0.07
    ä¼°è¨Ī
    0.07
     estimate
    0.07
    Activations Density 0.009%

    No Known Activations