© 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. 50671
    Prev
    Next
    INDEX
    Explanations

    comes as no surprise

    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
    ulton
    -0.07
    addock
    -0.07
    JAKARTA
    -0.07
     banged
    -0.07
    imetype
    -0.07
    ụn
    -0.07
    otle
    -0.07
    为使
    -0.07
    ä¸įæĹ©
    -0.07
    寧
    -0.07
    POSITIVE LOGITS
    ritte
    0.06
    注æĦı
    0.06
    示
    0.06
     McCarthy
    0.06
    çķĻæĦı
    0.06
    ãģĨãĤĭ
    0.06
    çŀ©çĽ®
    0.06
     contro
    0.06
     ilustr
    0.06
     lÆ°u
    0.06
    Activations Density 0.580%

    No Known Activations