© 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. 14005
    Prev
    Next
    INDEX
    Explanations

    direction opposite perpendicular parallel

    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
    åĽ¾çīĩæĪĸ
    -0.08
    ืà¹īà¸Ļ
    -0.08
    ssize
    -0.08
    éĺĻ
    -0.07
    纵横
    -0.07
    ä»»ä½ķä¿Ŀè¯ģ
    -0.07
    ä¾µçĬ¯äºĨ
    -0.07
    ä¿ĿæĮģäºĨ
    -0.07
     Hurt
    -0.07
    åħī顾
    -0.07
    POSITIVE LOGITS
    åıłåĬł
    0.10
    æĸ¹åIJij
    0.10
    ä¸įåĪ©
    0.09
    æĸ¹åIJijçļĦ
    0.09
     opposing
    0.09
    æľīåĪ©çļĦ
    0.09
     direction
    0.09
     aligned
    0.08
    æĬµæ¶Ī
    0.08
    è¿İéĿ¢
    0.08
    Activations Density 0.014%

    No Known Activations