© 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. 25622
    Prev
    Next
    INDEX
    Explanations

    interchangeably or values

    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»»ä½ķä¸Ģç§į
    -0.07
     necessarily
    -0.06
    åĴ¯
    -0.06
    çݯ路
    -0.06
    两çĤ¹
    -0.06
    åıĸåħ¶
    -0.06
     inherently
    -0.06
     âĢķ
    -0.06
    æĹłåı¯
    -0.06
    尽享
    -0.06
    POSITIVE LOGITS
     mostly
    0.10
    ä¼¼ä¹İæĺ¯
    0.10
    Pattern
    0.10
    ä¼¼ä¹İåľ¨
    0.10
     seemed
    0.10
    mostly
    0.10
    ä¼¼ä¹İ
    0.10
    çļĦä¸ĢäºĽ
    0.09
     seem
    0.09
     seems
    0.09
    Activations Density 0.036%

    No Known Activations