© 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. 57819
    Prev
    Next
    INDEX
    Explanations

    eigenstate transitions

    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
    ilog
    -0.08
    angan
    -0.08
    rhein
    -0.07
    åĴĮæĦıä¹ī
    -0.07
    SSI
    -0.07
    以ä¸ĭåĩł
    -0.07
    å¢ŀåĬłåĢ¼
    -0.07
    æ¢Ń
    -0.07
    ä»ĭçŁ³
    -0.06
    交éĻħ
    -0.06
    POSITIVE LOGITS
     bersangkutan
    0.07
     transition
    0.07
    alker
    0.07
    лин
    0.07
    transition
    0.07
    ransition
    0.07
    -transition
    0.07
     Transition
    0.07
    vf
    0.07
    trap
    0.07
    Activations Density 0.004%

    No Known Activations