© 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. 29085
    Prev
    Next
    INDEX
    Explanations

    for the purpose of

    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
    ága
    -0.08
    设æ³ķ
    -0.08
    odox
    -0.08
    osate
    -0.08
    çļĦä¼ĺçĤ¹
    -0.07
    abela
    -0.07
    æ¯ĽçĹħ
    -0.07
    enso
    -0.07
    åĴĮä¿¡æģ¯åĮĸ
    -0.07
    kanie
    -0.07
    POSITIVE LOGITS
    cek
    0.08
     purposes
    0.08
    çĶ¨çļĦ
    0.08
    å¿ħè¦ģãģª
    0.07
     purpose
    0.07
     szolgál
    0.07
     amacıyla
    0.07
    å¿ħéľĢçļĦ
    0.07
    åIJĮæĹ¶ä¹Ł
    0.07
    æīĢéľĢçļĦ
    0.07
    Activations Density 0.116%

    No Known Activations