© 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. 9506
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and salts

    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
    mise
    -0.07
    ÙģتÙĩ
    -0.07
    åĽ½å®¶è§Ħå®ļ
    -0.07
    åķĦ
    -0.07
    ailer
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    onte
    -0.07
    mani
    -0.07
    ecc
    -0.06
     hinweg
    -0.06
    POSITIVE LOGITS
    æ§Ľ
    0.07
    ä¸ĢéĹª
    0.07
    idor
    0.07
    odom
    0.07
    çĶ¨ä½ľ
    0.07
    isure
    0.07
     equivalents
    0.07
    çļĦåĩºçİ°
    0.07
    åı¯ä½ľä¸º
    0.07
    åij³çĶĺ
    0.07
    Activations Density 0.015%

    No Known Activations