© 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. 25539
    Prev
    Next
    INDEX
    Explanations

    minimally invasive

    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
    -containing
    -0.07
    èĢĮå¼ķèµ·çļĦ
    -0.07
    çĶ¨äºİæ²»çĸĹ
    -0.07
    ä¸Ģèµ·åĪĨ享
    -0.07
    érer
    -0.07
    æīĢå¼ķèµ·çļĦ
    -0.06
    èĪİ
    -0.06
    åĴĮåŃ¦ä¹ł
    -0.06
     mortal
    -0.06
    åĴĮå¤ĦçIJĨ
    -0.06
    POSITIVE LOGITS
     approach
    0.12
     approaches
    0.11
     methods
    0.11
     ë°©ë²ķìľ¼ë¡ľ
    0.10
     подÑħода
    0.09
    æĸ¹æ³ķè¿Ľè¡Į
    0.09
    วิà¸ĺี
    0.09
     ë°©ë²ķìĿĦ
    0.09
     Approach
    0.09
    æĸ¹æ³ķ
    0.09
    Activations Density 0.248%

    No Known Activations