© 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. 60396
    Prev
    Next
    INDEX
    Explanations

    lists date metadata transmission

    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
    евиÑĩ
    -0.08
    çħ§æł·
    -0.07
    ä¸įæĺ¯åIJĹ
    -0.07
    é¦ĸåħĪæĺ¯
    -0.07
    åıijæĢ§
    -0.07
    ÑħваÑĤ
    -0.07
    ŃĶ
    -0.06
    ÙģÙĩ
    -0.06
    gre
    -0.06
     пеÑĢв
    -0.06
    POSITIVE LOGITS
    幸
    0.08
    ippo
    0.07
    سات
    0.07
    opan
    0.07
    innan
    0.07
    害
    0.07
    리ìĬ¤
    0.06
    ebas
    0.06
    _ios
    0.06
    èĵ¬
    0.06
    Activations Density 0.001%

    No Known Activations