© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19584
    Prev
    Next
    INDEX
    Explanations

    determine characteristic cases

    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
    utto
    -0.07
    ä¹ı
    -0.07
     greeting
    -0.07
    èĵ
    -0.06
    å¹³æŶçļĦ
    -0.06
     greet
    -0.06
     seasoned
    -0.06
    常说çļĦ
    -0.06
    habit
    -0.06
    æ²¾
    -0.06
    POSITIVE LOGITS
     conject
    0.11
    åı¯æĥľçļĦæĺ¯
    0.08
     mysterious
    0.08
    ä½Ĩ缮åīį
    0.08
    Previously
    0.08
     elusive
    0.08
     mỼi
    0.08
    åĪ»çĶ»
    0.08
     cases
    0.08
    çĮľæĥ³
    0.08
    Activations Density 0.318%

    No Known Activations