© 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. 48783
    Prev
    Next
    INDEX
    Explanations

    tautomerization, forms, morphogenesis

    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
    ega
    -0.08
     graduating
    -0.07
    åıªèĥ½çĶ¨
    -0.07
    请ä¸ĭè½½
    -0.07
    otti
    -0.07
    åķĨ
    -0.07
     remaining
    -0.07
    arker
    -0.06
    éĩıåĬĽ
    -0.06
     trackers
    -0.06
    POSITIVE LOGITS
     spontaneously
    0.10
     fleeting
    0.09
     alternate
    0.09
    alternate
    0.09
     âĨĶ
    0.08
    转åĮĸçļĦ
    0.08
     Altern
    0.08
    Alternate
    0.08
    Forms
    0.08
    convert
    0.08
    Activations Density 0.007%

    No Known Activations