© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    sentence endings or questions

    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
    ä¸Ģ寸
    -0.08
    audi
    -0.08
    -indent
    -0.08
    çĦ¶å¤§
    -0.08
    olley
    -0.08
    IFA
    -0.07
    åı¯æĥ³
    -0.07
    į¼
    -0.07
    åĽłåľ°
    -0.07
    /datatables
    -0.07
    POSITIVE LOGITS
    äºijéľĦ
    0.07
    point
    0.06
    ena
    0.06
     deduct
    0.06
    æĥ¨åı«
    0.05
    mas
    0.05
    Era
    0.05
    pointer
    0.05
    常è§ĦçļĦ
    0.05
     mas
    0.05
    Activations Density 0.015%

    No Known Activations