© 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. 29571
    Prev
    Next
    INDEX
    Explanations

    explaining reasons or causes

    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
    æŃ¢
    -0.08
     surtout
    -0.07
    ä½Ĩèĩ³å°ij
    -0.06
     moh
    -0.06
    obia
    -0.06
    æĺ¯ä¸įæĺ¯
    -0.06
    åĩłä¹İæĺ¯
    -0.06
    odoro
    -0.06
     probably
    -0.06
    æĪij该
    -0.06
    POSITIVE LOGITS
    åıªæľīè¿Ļæł·
    0.14
    è¿Ļæł·åı¯ä»¥
    0.11
    è¿Ļæł·æīįèĥ½
    0.10
    edException
    0.09
    изи
    0.08
    å·¥ä½ľéľĢè¦ģ
    0.08
    à¸īะà¸Ļัà¹īà¸Ļ
    0.08
    è¿Ļæł·å°±åı¯ä»¥
    0.07
    ä¹IJæ¸ħ
    0.07
    .invalidate
    0.07
    Activations Density 0.099%

    No Known Activations