© 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. 34121
    Prev
    Next
    INDEX
    Explanations

    effective manipulation of light

    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
    çĴĢ
    -0.08
     hourly
    -0.08
    èĦļæīĭ
    -0.08
    该产åĵģ
    -0.07
    ifix
    -0.07
     ips
    -0.07
    æİĴçļĦ
    -0.07
     goof
    -0.07
    ÑĢаÑģпо
    -0.07
    åħ¬ç«ĭ
    -0.07
    POSITIVE LOGITS
     phenomena
    0.09
    缸äºĴä½ľçĶ¨
    0.09
     interactions
    0.09
    åĬ¨åĬĽåѦ
    0.08
     nonlinear
    0.08
     manifestations
    0.08
     dynamic
    0.08
    åIJ¸å¼ķäºĨä¼Ĺå¤ļ
    0.08
     dynam
    0.07
     Ferm
    0.07
    Activations Density 0.030%

    No Known Activations