© 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. 19899
    Prev
    Next
    INDEX
    Explanations

    resonance and related words

    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
    ories
    -0.09
     اÙĦÙħتØŃدة
    -0.09
    èµĦæºIJç½ij
    -0.08
    wards
    -0.08
    佬
    -0.08
    -Russian
    -0.08
    zioni
    -0.07
    å¯Įç¿ģ
    -0.07
    oriously
    -0.07
    -fashioned
    -0.07
    POSITIVE LOGITS
    ponce
    0.08
    å¥
    0.08
    haft
    0.07
    ÑĢа
    0.07
    ember
    0.07
    æĢ§çļĦ
    0.07
    loff
    0.07
    ponsible
    0.07
    aby
    0.07
    ×IJ×ķת
    0.07
    Activations Density 0.009%

    No Known Activations