© 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. 31034
    Prev
    Next
    INDEX
    Explanations

    must start now, number one, free to

    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
    å¸ĮæľĽå¯¹æĤ¨
    -0.10
    æĤ¨åı¯èĥ½
    -0.10
    æĥħåĨµè¿Ľè¡ĮäºĨ
    -0.09
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.09
    éľĢè¦ģ注æĦı
    -0.09
    åıĺæĪIJäºĨ
    -0.09
    ìĺ¤ëĭĪ
    -0.08
    imuth
    -0.08
    ä½łåı¯èĥ½
    -0.08
     dover
    -0.08
    POSITIVE LOGITS
    æīįè¡Į
    0.14
    èĩ³å°ij
    0.13
    èĩ³å°ijåľ¨
    0.13
     atleast
    0.13
     almeno
    0.12
    æīįèĥ½æľī
    0.11
    æīį好
    0.11
    è¿Ļæł·æīįèĥ½
    0.11
    æīįåı¯ä»¥
    0.11
    æīįèĥ½
    0.11
    Activations Density 0.492%

    No Known Activations