© 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. 18561
    Prev
    Next
    INDEX
    Explanations

    early-stage investments

    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
    æłijç«ĭ
    -0.07
    çIJĨ解为
    -0.06
    äºĪ以
    -0.06
    åĨħå¤ĸ
    -0.06
    itarian
    -0.06
    ¥IJ
    -0.06
    å¥ı
    -0.06
    anch
    -0.06
    abin
    -0.05
    绣
    -0.05
    POSITIVE LOGITS
    对éĤ£äºĽ
    0.12
    对ä¸ĢäºĽ
    0.11
    对åħ¶ä»ĸ
    0.10
    åIJĮæĹ¶å¯¹
    0.09
    å¸Ĥåľºå¯¹
    0.09
    对äºİä¸ĢäºĽ
    0.08
    æĹ¶å¯¹
    0.08
    æīĢ以对äºİ
    0.08
    è§ĦåĪĴ建设
    0.08
    人åijĺ对
    0.08
    Activations Density 1.217%

    No Known Activations