© 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. 23111
    Prev
    Next
    INDEX
    Explanations

    selection criteria

    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
    agence
    -0.06
    ãģĽãģĦ
    -0.06
    æĬ¥åijĬæĺ¾ç¤º
    -0.06
    oons
    -0.06
    æł¼è°ĥ
    -0.06
    ç®ĢæŀIJ
    -0.06
    .exports
    -0.06
     agence
    -0.06
    UMA
    -0.06
    ctime
    -0.06
    POSITIVE LOGITS
    istol
    0.10
    æīĢéľĢè¦ģçļĦ
    0.10
    æīĢéľĢçļĦ
    0.09
     needed
    0.08
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    0.08
    éľĢè¦ģçļĦ
    0.08
    ä¹ĭçĶ¨
    0.08
     Kitt
    0.08
    æīĢéľĢ
    0.08
     potreb
    0.08
    Activations Density 0.195%

    No Known Activations