© 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. 9169
    Prev
    Next
    INDEX
    Explanations

    performance Channel

    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
    rok
    -0.07
    мок
    -0.07
    ollo
    -0.07
    رÙĤ
    -0.07
    Ùģر
    -0.07
    ÑģÑĤе
    -0.06
    clare
    -0.06
    anho
    -0.06
    hir
    -0.06
    aira
    -0.06
    POSITIVE LOGITS
    åIJĦç§įåIJĦæł·
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    åĭĩå¾Ģ缴åīį
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    à¹Ī
    0.07
    anium
    0.07
    æĪijæĥ³è¦ģ
    0.07
    è·ĥè·ĥ欲è¯ķ
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ä»ĭçŁ³
    0.07
    Activations Density 0.004%

    No Known Activations