© 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. 19370
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    æķĻç§ij书
    -0.07
    ingan
    -0.07
    åĪļ好
    -0.07
    çIJĨäºĭ
    -0.07
    æķĻç§ij
    -0.06
    udit
    -0.06
    ochen
    -0.06
    åºĥåijĬãģ¯
    -0.06
    ramer
    -0.06
    红èĬ±
    -0.06
    POSITIVE LOGITS
    åĪ°çİ°åľº
    0.08
    代ä¹ĭ
    0.07
    ilos
    0.07
    erings
    0.07
    èĭĹ
    0.07
    èŁĨ
    0.07
     Sec
    0.07
    æĸĹ士
    0.07
    elin
    0.07
    ×ķר×Ļ×Ŀ
    0.07
    Activations Density 0.026%

    No Known Activations