© 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. 16400
    Prev
    Next
    INDEX
    Explanations

    selected / assignment

    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
    uber
    -0.07
    æĸ¹åľĨ
    -0.07
     sc
    -0.07
    è¿ĶãģĹ
    -0.06
    缩水
    -0.06
    ä¼łæŁĵæĢ§
    -0.06
    ubat
    -0.06
    >+
    -0.06
    两èĢħ
    -0.06
    两å±Ĥ
    -0.06
    POSITIVE LOGITS
    åľ°ä½į
    0.09
    -elected
    0.09
    -selected
    0.08
    è½®æį¢
    0.08
    chosen
    0.08
    åĴĮéĿŀ
    0.08
     chosen
    0.07
     Assignment
    0.07
    .selected
    0.07
     assignment
    0.07
    Activations Density 0.001%

    No Known Activations