© 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. 57732
    Prev
    Next
    INDEX
    Explanations

    features and technology

    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
    udel
    -0.07
     inilah
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    ä¸Ĭè¿°
    -0.06
    ecen
    -0.06
     REFER
    -0.06
    ä½łåĪ«
    -0.06
     ìľĦìĿĺ
    -0.06
    ithe
    -0.06
    æĬĬä½ł
    -0.06
    POSITIVE LOGITS
    è¿Ļé¡¹å·¥ä½ľ
    0.09
    æŃ¤é¡¹
    0.08
    ãģĵãĤĮãĤĤ
    0.08
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    à¹Ģรืà¹Īà¸Ńà¸ĩà¸Ļีà¹ī
    0.07
    çļĦä¸Ģå¹´
    0.07
    çļĦæıIJé«ĺ
    0.07
    äºİæѤ
    0.07
    /native
    0.07
    è¿Ļæĸ¹éĿ¢
    0.07
    Activations Density 0.323%

    No Known Activations