© 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. 28854
    Prev
    Next
    INDEX
    Explanations

    distinctive, observable, stable, scientific terms

    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
    æ·±å±Ĥ次
    -0.08
    åħ¨åĬĽæĶ¯æĮģ
    -0.07
    æ½Ķ
    -0.07
    ewis
    -0.07
    _INFINITY
    -0.07
    åıªçŁ¥éģĵ
    -0.07
    telen
    -0.07
     undecided
    -0.07
    æĽ´æ·±
    -0.07
     concluded
    -0.07
    POSITIVE LOGITS
    便äºİ
    0.18
    æĺĵäºİ
    0.16
    以便äºİ
    0.15
    åı¯ä¾Ľ
    0.13
     observable
    0.13
    çľĭå¾Ĺè§ģ
    0.13
    æĸ¹ä¾¿
    0.12
    以便
    0.12
     visible
    0.12
     conveniently
    0.12
    Activations Density 0.266%

    No Known Activations