© 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. 22773
    Prev
    Next
    INDEX
    Explanations

    sample size maintenance programs

    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
    ovel
    -0.09
    emper
    -0.08
    AuthProvider
    -0.08
    åĩºå¸ŃäºĨ
    -0.08
    oviÄĩ
    -0.08
    Ĥ¹
    -0.08
     ORIG
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    ä¹ł
    -0.07
    ä¸įæ³ķ
    -0.07
    POSITIVE LOGITS
    é¢Ħä¼°
    0.08
    åĪ°æŶåĢĻ
    0.08
     planning
    0.07
    缩å°ı
    0.07
     sampling
    0.07
    çĶĺ
    0.07
    åĩij
    0.07
     Sampling
    0.07
    估计
    0.07
    æĬ½æł·
    0.07
    Activations Density 0.012%

    No Known Activations