© 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. 49942
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    åĪ°ä»Ĭ天
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.07
    opedia
    -0.07
    vain
    -0.07
    å¾Īæĺ¾çĦ¶
    -0.07
     herein
    -0.07
    家åĸ»
    -0.06
     Schau
    -0.06
    ardo
    -0.06
    AINS
    -0.06
    POSITIVE LOGITS
    ä¸įæŃ¢
    0.08
    ä¸į代表
    0.07
    or
    0.07
    REN
    0.07
    ä½Ĩä¸įæĺ¯
    0.07
    ä¸įçĦ¶
    0.07
    ä½Ĩä¸į
    0.07
     otherwise
    0.07
    ä¸įéĹ®
    0.07
    agar
    0.06
    Activations Density 0.655%

    No Known Activations