© 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. 62105
    Prev
    Next
    INDEX
    Explanations

    succession of power or throne

    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
    ä¸įæ¼ı
    -0.08
    porté
    -0.08
    ilar
    -0.08
    allel
    -0.07
    ortable
    -0.07
    indi
    -0.07
    perse
    -0.07
    èŀįåĪ¸
    -0.07
    åĴ«å°º
    -0.07
    GIN
    -0.07
    POSITIVE LOGITS
    æݥ任
    0.12
     succession
    0.12
    æİ¥æĽ¿
    0.12
     interim
    0.12
    è¿ĩ渡
    0.11
    äº¤æĽ¿
    0.10
    继æī¿
    0.10
     successor
    0.09
     reign
    0.09
     successors
    0.09
    Activations Density 0.464%

    No Known Activations