© 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. 25666
    Prev
    Next
    INDEX
    Explanations

    able to

    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
    è°ģä¼ļ
    -0.09
    è¦ģä¹Īæĺ¯
    -0.08
    æĢİèĥ½
    -0.08
    akkan
    -0.08
    å¹²ä»Ģä¹Ī
    -0.07
    æĢİä¹Īèĥ½
    -0.07
    vince
    -0.07
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    -0.07
     McA
    -0.07
    æĺ¯å¤ļä¹Ī
    -0.07
    POSITIVE LOGITS
    ï¼Ł
    0.08
    arger
    0.07
    æŁIJç§į
    0.07
    Äĥm
    0.07
    ilo
    0.07
    ï¼Łï¼ī
    0.07
    çŃīåIJĮäºİ
    0.07
    estes
    0.07
    à¸ģà¹ĩà¹Ħà¸Ķà¹ī
    0.06
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.06
    Activations Density 0.034%

    No Known Activations