© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    good or buy one

    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
    ä¸Ģ缴åĪ°
    -0.07
    apos
    -0.07
    å¡ģ
    -0.06
    ä¸Ģä¸ĭåŃIJ
    -0.06
    å¯ŀ
    -0.06
    å¤ĸåĽ½è¯Ń
    -0.06
     Tew
    -0.06
    ÑĨо
    -0.06
    å¸ľ
    -0.06
    缴åĪ°
    -0.06
    POSITIVE LOGITS
    ä¸Ńä¹ĭ
    0.10
    å¾Ĺåħ¶
    0.10
    èĢĮä¸į
    0.09
    ä¸ĬåĬł
    0.09
    ä¹ĭä¸į
    0.09
    管æīĢ
    0.09
    ä¸Ńæľī
    0.08
    家åºĹ
    0.08
    äºĭæĪIJ
    0.08
    åħ¶æīĢ
    0.08
    Activations Density 0.055%

    No Known Activations