© 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. 21864
    Prev
    Next
    INDEX
    Explanations

    focus on values and objectives

    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
    endra
    -0.07
    éħįåIJĪ
    -0.07
    æīĵèµ·
    -0.07
    ä¸įæį¢
    -0.06
    åŀ¢
    -0.06
    积æŀģéħįåIJĪ
    -0.06
    åĬłå¥½åıĭ
    -0.06
    åħĭé²ģ
    -0.06
    ostro
    -0.06
    æĮ¯
    -0.06
    POSITIVE LOGITS
    çŀ»
    0.07
    å¾Ģ
    0.07
     subsystem
    0.07
    第ä¸īæŃ¥
    0.07
    upert
    0.07
    åŃIJç³»ç»Ł
    0.07
    并éĩį
    0.07
    illen
    0.07
    ä¸īæĺ¯
    0.07
    omor
    0.07
    Activations Density 0.271%

    No Known Activations