© 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. 50910
    Prev
    Next
    INDEX
    Explanations

    two numbers are related

    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
    åĩŃåĢŁåħ¶
    -0.09
     **:**
    -0.08
    MASK
    -0.08
     ÑĢода
    -0.08
    embed
    -0.08
    ZER
    -0.08
    λοÏħ
    -0.08
    åĽłä¸ºåħ¶
    -0.08
    हित
    -0.08
    è´¹å°Ķ
    -0.08
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    æľī两ç§į
    0.07
    åīįèĢħ
    0.06
    çļĦè¿Ļä¸Ģ
    0.06
    è¿Ļæĸ¹éĿ¢
    0.06
    åIJİèĢħ
    0.06
    æģ°æģ°
    0.06
    aro
    0.06
     phrase
    0.06
    æ´»
    0.06
    Activations Density 0.202%

    No Known Activations