© 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. 32635
    Prev
    Next
    INDEX
    Explanations

    introduction, background, or segments

    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
    retti
    -0.07
     Pej
    -0.07
    æĪij便
    -0.07
    ipun
    -0.07
    endr
    -0.07
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.06
    .Assert
    -0.06
     maggiormente
    -0.06
    agged
    -0.06
    æĬĢå·§åĴĮ
    -0.06
    POSITIVE LOGITS
    ÑĥÑĤÑĮ
    0.10
    ãģĿãĤĤãģĿãĤĤ
    0.09
    åŁºæľ¬æ¦Ĥ念
    0.09
     basics
    0.08
    åŁºæľ¬åİŁçIJĨ
    0.08
    人åıĹ伤
    0.08
    å®ļä¹ī
    0.08
     Basics
    0.07
    æĪij们éĥ½çŁ¥éģĵ
    0.07
    åŁºæľ¬è¦ģæ±Ĥ
    0.07
    Activations Density 0.008%

    No Known Activations