© 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. 63052
    Prev
    Next
    INDEX
    Explanations

    bigger adventures

    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
    æĹºçĽĽ
    -0.08
    allest
    -0.08
    ama
    -0.07
    ually
    -0.07
    æĤ¨å½ĵåīįçļĦä½įç½®
    -0.07
    erweise
    -0.07
    asks
    -0.07
    ramer
    -0.07
    orem
    -0.07
    appa
    -0.07
    POSITIVE LOGITS
    isty
    0.08
     proverb
    0.07
    enance
    0.07
    à¹ĥà¸Ī
    0.07
     дела
    0.07
     делÑĥ
    0.07
    åij³åĦ¿
    0.06
    äºĭåĦ¿
    0.06
     ferment
    0.06
    å®Ŀå±±
    0.06
    Activations Density 2.050%

    No Known Activations