© 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. 14508
    Prev
    Next
    INDEX
    Explanations

    drug - bio - chem - liability

    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
    oriously
    -0.08
    ÑĤик
    -0.07
    mico
    -0.07
    udel
    -0.07
    æģº
    -0.07
     ugyanis
    -0.07
    Ó©Ó©
    -0.07
    иÑĩ
    -0.07
     theoret
    -0.07
    ört
    -0.07
    POSITIVE LOGITS
    éķ¿æľŁä»İäºĭ
    0.07
    https
    0.07
    idane
    0.06
    大å®Ĺ
    0.06
    elen
    0.06
    ãģªãģĭ
    0.06
    Visit
    0.06
     https
    0.06
    è¶ĬæĹ©
    0.06
    -hide
    0.06
    Activations Density 0.009%

    No Known Activations