© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    段
    -0.08
    ed
    -0.07
     ë§Įíģ¼
    -0.06
    æ¹¾
    -0.06
    à·Ģà·ı
    -0.06
    zer
    -0.06
    ÃģL
    -0.06
    forth
    -0.06
    edes
    -0.06
    Em
    -0.06
    POSITIVE LOGITS
    omid
    0.08
    opyright
    0.08
    æĹ¥åĩºçĶŁ
    0.08
    :border
    0.07
    FileInfo
    0.07
    ableView
    0.07
    omit
    0.07
    身临åħ¶å¢ĥ
    0.07
    FileVersion
    0.07
    aider
    0.07
    Activations Density 0.006%

    No Known Activations