© 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. 64674
    Prev
    Next
    INDEX
    Explanations

    effects on other

    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
    çī¹æĸ¯
    -0.08
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    -0.07
    tps
    -0.07
     stille
    -0.07
    ר×ij
    -0.06
    cors
    -0.06
    åľ¨æ¯ı个
    -0.06
    lade
    -0.06
    azzi
    -0.06
    åĿļ强çļĦ
    -0.06
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.10
     supposedly
    0.09
    åħ¶çī¹å¾ģåľ¨äºİ
    0.07
    å±ħçĦ¶
    0.07
    åºĬä¸ĬçĶ¨åĵģ
    0.07
    )?.
    0.07
    以æѤæĿ¥
    0.07
    çī¹å®ļ
    0.07
    彦
    0.07
    èģĮä¸ļèĥ½åĬĽ
    0.07
    Activations Density 0.027%

    No Known Activations