© 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. 27404
    Prev
    Next
    INDEX
    Explanations

    owner groups

    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
    ç§ijåijĺ
    -0.08
    æī¾äºº
    -0.07
    uzzle
    -0.07
    åĪ«äººçļĦ
    -0.07
    æŃ»åIJİ
    -0.07
    产åĵģåı¬åĽŀ
    -0.07
    åŃ©åŃIJæĺ¯
    -0.07
    ÃīM
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    å¸ĤæĶ¿åįı
    -0.07
    POSITIVE LOGITS
    èī¯å¿ĥ
    0.09
    relevant
    0.08
     relevant
    0.08
     selaku
    0.08
     representatives
    0.08
    levant
    0.07
    otify
    0.07
     involved
    0.07
    代表
    0.07
     Runde
    0.07
    Activations Density 0.679%

    No Known Activations