© 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. 14391
    Prev
    Next
    INDEX
    Explanations

    .ft commands, restore, revert

    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
    aed
    -0.08
    оÑĤÑĢе
    -0.06
    彤
    -0.06
    anns
    -0.06
    çŁ¥å·±
    -0.06
     Happ
    -0.06
    inium
    -0.06
    umpy
    -0.06
    åıijå±ķæľºéģĩ
    -0.06
     worse
    -0.06
    POSITIVE LOGITS
    æģ¢å¤įæŃ£å¸¸
    0.15
    æģ¢å¤įåĪ°
    0.12
    æģ¢å¤į
    0.12
    æģ¢å¾©
    0.11
    .restore
    0.11
    restore
    0.11
    åĨįãģ³
    0.10
    æĶ¶åĽŀ
    0.10
     revert
    0.10
    ãģ«æĪ»
    0.10
    Activations Density 0.131%

    No Known Activations