© 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. 56663
    Prev
    Next
    INDEX
    Explanations

    magnetism

    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
    çĵľ
    -0.08
    åĬłä»¥
    -0.07
    è¦ģçŁ¥éģĵ
    -0.06
    اص
    -0.06
    ç¨Ģ
    -0.06
    éijij
    -0.06
    å§
    -0.06
    çĴ§
    -0.06
    é¢ĩ
    -0.06
     tot
    -0.05
    POSITIVE LOGITS
    è¿ĺä¸İ
    0.12
    è¿ĺåĮħæĭ¬
    0.11
    è¿ĺåı¯ä»¥éĢļè¿ĩ
    0.11
    并éĿŀæĺ¯
    0.11
    è¿ĺåı¯ä»¥
    0.10
    è¿ĺ表示
    0.10
    è¿ĺåı¯èĥ½
    0.10
    以å¤ĸãģ«ãĤĤ
    0.10
    çļĦåħ¶ä»ĸ
    0.10
    è¿ĺ对
    0.10
    Activations Density 0.010%

    No Known Activations