© 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. 46012
    Prev
    Next
    INDEX
    Explanations

    end punctuation like ). )) );

    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
    ë¥ĺ를
    -0.08
    æŀĦ建åĴĮè°IJ
    -0.08
    unnel
    -0.08
    æŀ¶æŀĦåĽ¾
    -0.08
    tereo
    -0.08
     troub
    -0.08
    ulat
    -0.08
    é«ĺæĺİ
    -0.08
    führ
    -0.08
    à¸Ĭัà¹Īว
    -0.07
    POSITIVE LOGITS
    確ãģĭãģ«
    0.07
    æĺ¾çĦ¶
    0.07
    確ãģĭ
    0.07
     neither
    0.07
     clearly
    0.07
    ç¡®å®ŀ
    0.06
    2
    0.06
    ät
    0.06
    çľĭåĩº
    0.06
    oya
    0.06
    Activations Density 0.008%

    No Known Activations