© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11729
    Prev
    Next
    INDEX
    Explanations

    MPC, This, The, Right, For

    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
    é¦ĸåħĪæĺ¯
    -0.09
    acker
    -0.07
    atham
    -0.07
    æĪij们认为
    -0.07
    éĤ£ä¸į
    -0.06
    ä»ĸæĥ³
    -0.06
    æĺ¾çĦ¶æĺ¯
    -0.06
    é¦ĸåħĪ
    -0.06
    .fd
    -0.06
    åĵĩ
    -0.06
    POSITIVE LOGITS
    æľįåĬ¡çĥŃ线
    0.08
    ydi
    0.08
    ç»ļ
    0.07
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.07
    à¹īà¸Ńม
    0.07
    ikka
    0.07
     ãģªãģĬ
    0.07
    ç·Ĵ
    0.07
    ãģĭãģĴ
    0.07
    ¹
    0.07
    Activations Density 0.030%

    No Known Activations