© 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. 62591
    Prev
    Next
    INDEX
    Explanations

    focus

    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
    æĸ°åĬ¨èĥ½
    -0.07
    åĻ
    -0.07
    baugh
    -0.07
     leng
    -0.07
    ycin
    -0.07
    ãĥ¡ãĥ«
    -0.07
    稳ä¸Ń
    -0.07
    åı¦è¡ĮéĢļçŁ¥
    -0.07
    анее
    -0.07
    thag
    -0.07
    POSITIVE LOGITS
    æĺ¯éĴĪ对
    0.09
    客ä½ĵ
    0.09
     Focus
    0.09
     Scope
    0.09
     focus
    0.09
    çĦ¦çĤ¹
    0.08
    çļĦ对象
    0.08
    åıijçĶŁåľ¨
    0.08
    Focus
    0.08
    æĥłåıĬ
    0.08
    Activations Density 0.306%

    No Known Activations