© 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. 40492
    Prev
    Next
    INDEX
    Explanations

    polynomials and telecommunications

    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
     axial
    -0.08
    avenport
    -0.07
    lish
    -0.07
    è½´åIJij
    -0.07
    ax
    -0.07
    orthand
    -0.07
    ÑıÑĤи
    -0.07
     basi
    -0.07
    oha
    -0.07
    å¿ĥ缮ä¸Ń
    -0.07
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭ好
    0.08
    æ¯ı次éĥ½
    0.08
    æIJŃ
    0.08
    æ¯ı次
    0.08
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.08
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.07
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.07
    ÃŃdu
    0.07
    .Serial
    0.07
    尼奥
    0.07
    Activations Density 0.028%

    No Known Activations