© 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. 11212
    Prev
    Next
    INDEX
    Explanations

    ending

    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
    æĹ©æĺ¥
    -0.09
    æĹ©
    -0.08
     Früh
    -0.08
    æĹ©çĽĺ
    -0.08
    å¹´ä¸ĢåŃ£åº¦
    -0.08
    æĹ©æĻ¨
    -0.08
    æĹ©é¥Ń
    -0.07
    æĹ©æľŁçļĦ
    -0.07
    ä¼Ĭå§ĭ
    -0.07
     mattina
    -0.07
    POSITIVE LOGITS
    å°¾
    0.13
    å°¾éĥ¨
    0.12
     tail
    0.12
    æľ«ç«¯
    0.12
    åľ¨æľĢåIJİ
    0.11
    dern
    0.11
    æľ«
    0.11
    _tail
    0.11
    尾页
    0.11
    æĶ¶å°¾
    0.11
    Activations Density 0.281%

    No Known Activations