© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12003
    Prev
    Next
    INDEX
    Explanations

    you seem

    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
    leos
    -0.08
    ä¸įå·®
    -0.07
    森æŀĹ
    -0.07
    éĶĻè¿ĩçļĦ
    -0.07
    éĶĻ失
    -0.07
    ä¸ĩäºĭ
    -0.07
    ottom
    -0.07
    forest
    -0.07
     forest
    -0.07
    gnore
    -0.07
    POSITIVE LOGITS
    ill
    0.08
     realistically
    0.08
    ä¸įåIJĪçIJĨ
    0.07
    å±ħçĦ¶
    0.07
     unrealistic
    0.07
    ä¸įèĩª
    0.07
    æĮīçIJĨ
    0.07
    Pods
    0.07
    anya
    0.07
    çĸ
    0.07
    Activations Density 0.061%

    No Known Activations