© 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. 46481
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    æij¹
    -0.06
     Brus
    -0.06
    çĭ©
    -0.06
    åħ¬åı¸ä¸ļåĬ¡
    -0.06
    èѬ
    -0.06
    ¾
    -0.06
    å¯Ĥ
    -0.06
    å¡ĺ
    -0.06
    èĹ©
    -0.06
    èı
    -0.06
    POSITIVE LOGITS
    InParameter
    0.08
    unga
    0.08
    Õ¡Õ½
    0.07
    ÙĦÙĤ
    0.07
    ëłĪìĬ¤
    0.07
    èıģèĭ±
    0.07
     héro
    0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.07
    ampo
    0.07
    uman
    0.07
    Activations Density 0.030%

    No Known Activations