© 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. 60856
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
    Ùĭ
    -0.06
     relationship
    -0.06
    ands
    -0.06
    以身
    -0.06
    讲
    -0.06
    说罢
    -0.06
     =
    -0.06
    à¸ĸ
    -0.06
    çŁ¥éģĵäºĨ
    -0.06
     Relationship
    -0.05
    POSITIVE LOGITS
    istan
    0.09
    osit
    0.08
    OURS
    0.08
    neu
    0.08
    æѤè¡Į
    0.08
    лайн
    0.08
    çĴĢ
    0.08
    зÑĸ
    0.08
    éĶµ
    0.08
    CommandLine
    0.08
    Activations Density 0.072%

    No Known Activations