© 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. 31257
    Prev
    Next
    INDEX
    Explanations

    links, website addresses, and authorship statements

    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
     nis
    -0.08
    ç½ijé¦ĸ页
    -0.06
    orter
    -0.06
    æŃ£åĢ¼
    -0.06
    éĥ¨èIJ½å®¢
    -0.06
    /port
    -0.06
    .setdefault
    -0.06
    èĥ½å¤Łå¸®åĬ©
    -0.06
    invent
    -0.06
    ä¸ĢæĹ¦è¢«
    -0.06
    POSITIVE LOGITS
    kens
    0.08
    èĭı丹
    0.07
    ãģįãģĮ
    0.07
    çłģé¾Ħ
    0.07
    æł¼å°Ķ
    0.07
     tarafından
    0.07
    sockopt
    0.07
    ulte
    0.07
    ä½łåij¢
    0.07
    çĤİçĤİ
    0.06
    Activations Density 0.225%

    No Known Activations