© 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. 23135
    Prev
    Next
    INDEX
    Explanations

    bullets or symbols followed by text

    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
    ounty
    -0.07
    yson
    -0.07
    æĪij便
    -0.07
    æĥħåĨµè¯´æĺİ
    -0.07
    ç¨į
    -0.06
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.06
    åľ¨æĪijçľĭæĿ¥
    -0.06
    å¦Ĥä¸ĭ
    -0.06
    quier
    -0.06
    赫çĦ¶
    -0.06
    POSITIVE LOGITS
    æ°´æĺ¯
    0.11
    æķĻèĤ²æĺ¯
    0.09
    ç»Ŀ大å¤ļæķ°
    0.09
    åĬŁèĥ½æĺ¯
    0.09
    ä¸įè¦ģåľ¨
    0.09
    ç³»ç»Łæĺ¯
    0.09
     beware
    0.09
    èĩªå·±æĺ¯
    0.09
    æĢ§æĺ¯
    0.09
    è¦ģç»ı常
    0.08
    Activations Density 0.020%

    No Known Activations