© 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. 3969
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    åħ¬åı¸ä»¥
    -0.08
    人以
    -0.08
    äººä»¬åľ¨
    -0.08
    åįķä½įåıĤåĬł
    -0.08
    å±Ĥé«ĺ
    -0.08
    人åĪ°
    -0.08
    æķıæĦŁçļĦ
    -0.08
    à»ī
    -0.08
    产åĵģåľ¨
    -0.08
    æľ¬äººåľ¨
    -0.07
    POSITIVE LOGITS
    åľ°ä½į
    0.08
    igh
    0.07
    çļĦåľ°ä½į
    0.06
    以åıĬåľ¨
    0.06
    poses
    0.06
    æīĢåıĹ
    0.06
    åľ°ä½įçļĦ
    0.06
    izes
    0.06
    åľ°ä½įåĴĮ
    0.06
    Ñħам
    0.06
    Activations Density 0.012%

    No Known Activations