© 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. 29626
    Prev
    Next
    INDEX
    Explanations

    possessive form followed by word

    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
    adah
    -0.06
    úm
    -0.06
    æľīæĸ°
    -0.06
    æĥħå½¢
    -0.06
    agno
    -0.06
    æĿ¥èĩª
    -0.06
    ah
    -0.06
     testimony
    -0.05
    åħ¬åı¸åıijå±ķ
    -0.05
     Gang
    -0.05
    POSITIVE LOGITS
    arder
    0.09
    -wide
    0.09
    åIJİæĦŁ
    0.08
    èµĸ以
    0.08
    ë¦Ħ
    0.08
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.08
    åľ¨å®ĥ
    0.08
    aea
    0.08
    ullet
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    Activations Density 0.177%

    No Known Activations