© 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. 18262
    Prev
    Next
    INDEX
    Explanations

    legal provisions or document sections

    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
    è¾¾åħĭ
    -0.07
    egn
    -0.07
    roz
    -0.07
    igy
    -0.07
    èħ¹åľ°
    -0.06
    beck
    -0.06
    两ç§į
    -0.06
    áĭ¨
    -0.06
    åľŁåľ°æĬµæĬ¼
    -0.06
    æīİæīİå®ŀ
    -0.06
    POSITIVE LOGITS
     shall
    0.10
    ä¸įå¾Ĺ
    0.10
    åīį款
    0.10
    ä¸įå¾Ĺ使çĶ¨
    0.09
    è§Ħå®ļ
    0.09
    è§Ħå®ļäºĨ
    0.08
     subparagraph
    0.08
     provisions
    0.08
    çĶŁæķĪ
    0.08
    shall
    0.08
    Activations Density 0.044%

    No Known Activations