© 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. 17650
    Prev
    Next
    INDEX
    Explanations

    list item or code comment markers

    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
    çļĦ
    -0.08
    cript
    -0.07
    sl
    -0.07
    ÙĨ
    -0.07
    ÑīеÑĤ
    -0.07
    庶
    -0.07
    spinner
    -0.06
    stub
    -0.06
    ãģĻãģ¿
    -0.06
     Misc
    -0.06
    POSITIVE LOGITS
    oen
    0.07
    avier
    0.07
    代ä¹ĭ
    0.07
    è¿ħéĢŁçļĦ
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    ä¹ĭ忧
    0.07
    åĪ°å¦Ĥä»Ĭ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    åŃ¦ä¹łä¸Ĭ
    0.07
    å®ĥæĺ¯ä¸Ģç§į
    0.06
    Activations Density 0.001%

    No Known Activations