© 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. 12535
    Prev
    Next
    INDEX
    Explanations

    phrases ending with right?

    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
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    -0.09
    ÑİÑĢе
    -0.09
    å±ħçĦ¶æĺ¯
    -0.08
    gnore
    -0.08
    ç«ŁçĦ¶æĺ¯
    -0.08
    åĪĩå®ŀå¢ŀ强
    -0.08
    anship
    -0.08
    rone
    -0.08
    acity
    -0.08
    åĪ°åºķæľīå¤ļ
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Ł
    0.07
    Ùĭ
    0.07
    uz
    0.07
    Ø·
    0.06
    à¸Ħะ
    0.06
    fund
    0.06
    fek
    0.06
    gj
    0.06
     Cousins
    0.06
    ä¸įèĥ½åĨį
    0.05
    Activations Density 0.029%

    No Known Activations