© 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. 8743
    Prev
    Next
    INDEX
    Explanations

    key components

    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
    宣åijĬ
    -0.07
    ç«Ł
    -0.07
    åĴ±
    -0.07
    å±ħçĦ¶
    -0.07
    åijĬ
    -0.07
    å¾®æľº
    -0.07
    kken
    -0.07
     blah
    -0.06
    å¼ķåĩº
    -0.06
    å²ij
    -0.06
    POSITIVE LOGITS
     OECD
    0.09
     disag
    0.08
    éĩįçĤ¹é¢ĨåŁŁ
    0.08
     recommendations
    0.08
     Recommendation
    0.08
    ellas
    0.08
     Recommendations
    0.08
    ä¸ĭåĨ³å¿ĥ
    0.08
     policymakers
    0.08
    ancar
    0.08
    Activations Density 0.309%

    No Known Activations