© 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. 26112
    Prev
    Next
    INDEX
    Explanations

    conclusion or desired result

    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
     gác
    -0.08
    rie
    -0.08
     হয়à§ĩ
    -0.07
    :not
    -0.07
    urray
    -0.07
    entially
    -0.07
    reja
    -0.07
    -det
    -0.07
    earch
    -0.07
    ights
    -0.07
    POSITIVE LOGITS
     desired
    0.07
    çĿ¦
    0.06
     sought
    0.06
    æł¼é²ģ
    0.06
    ä¸İå°ı
    0.06
    é²ģ
    0.06
    oldt
    0.06
    uccio
    0.06
    urt
    0.06
    å¸
    0.06
    Activations Density 0.008%

    No Known Activations