© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    complex compounds and their properties

    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
    abouts
    -0.08
    ĭ
    -0.07
    wards
    -0.07
    ecess
    -0.07
    ested
    -0.07
    á»ĥu
    -0.07
    annis
    -0.07
    akup
    -0.07
    länd
    -0.07
    ham
    -0.06
    POSITIVE LOGITS
    veille
    0.09
    æĹłéĹ´
    0.09
    kke
    0.09
    laÅŁ
    0.08
    eur
    0.08
    atic
    0.08
    elor
    0.08
    åIJĪçī©
    0.08
     пеÑĢедаÑĩ
    0.07
    edés
    0.07
    Activations Density 0.031%

    No Known Activations