© 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. 64995
    Prev
    Next
    INDEX
    Explanations

    direction toward

    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
    寡
    -0.07
    urut
    -0.07
    å·¡
    -0.07
    scy
    -0.06
    wright
    -0.06
    ä¸įäºĨçļĦ
    -0.06
    rew
    -0.06
    è§ģä¹ł
    -0.06
    els
    -0.06
    åIJĦåı¸
    -0.06
    POSITIVE LOGITS
    æĸ¹åIJij
    0.12
     directions
    0.11
    çļĦæĸ¹åIJij
    0.11
    æĸ¹åIJijçļĦ
    0.11
     direction
    0.10
    æĸ¹åIJijåĴĮ
    0.09
    å¹³è¡Į
    0.09
    direction
    0.09
    åIJijå¤ĸ
    0.09
     ë°©íĸ¥ìľ¼ë¡ľ
    0.09
    Activations Density 0.005%

    No Known Activations