© 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. 47515
    Prev
    Next
    INDEX
    Explanations

    company names and roles

    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
    ÐijÐļ
    -0.07
    è¡ĮæĶ¿éĻ¢
    -0.07
    cese
    -0.06
    Attrs
    -0.06
    å±ħå§Ķä¼ļ
    -0.06
    骨
    -0.06
    à¹Ģà¸Ĥà¹īาà¹Ħà¸Ľ
    -0.06
    wers
    -0.06
    หà¸Ļา
    -0.06
    èĩªä½ľ
    -0.06
    POSITIVE LOGITS
    ilst
    0.08
    ä¸Ńå¿ĥå·¥ä½ľ
    0.08
     projects
    0.07
     kompleks
    0.07
     grunt
    0.07
     doomed
    0.07
    .assign
    0.07
    åij½é¢ĺ
    0.07
    complex
    0.07
    éĩijåŃĹ
    0.07
    Activations Density 0.825%

    No Known Activations