© 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. 13721
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or qualities

    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
    æľ¬åĵģ
    -0.07
    æľ¬åħ¬åı¸
    -0.07
    ä¸Ĭè¿Ľå¿ĥ
    -0.07
     cic
    -0.06
    æĮĩå®ļåľ°çĤ¹
    -0.06
    꽤
    -0.06
    ä¿ĿæĬ¤èĩªå·±
    -0.06
    æıIJåīįåģļ好
    -0.06
    åħ±åIJĮè¿ĽæŃ¥
    -0.06
    êµīìŀ¥
    -0.06
    POSITIVE LOGITS
    å®
    0.09
    对æĪijåĽ½
    0.09
    主ä½ĵçļĦ
    0.09
    å·²çĦ¶
    0.08
    è¯Ŀè¯Ń
    0.08
    åijĪçİ°åĩº
    0.08
    åѦçķĮ
    0.08
    æł¼æĸ¯
    0.08
    建æŀĦ
    0.08
    åĨ³å®ļçĿĢ
    0.08
    Activations Density 0.014%

    No Known Activations