© 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. 56729
    Prev
    Next
    INDEX
    Explanations

    and lists

    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
    gence
    -0.08
    æĬķèµĦæĪĸ
    -0.08
    ibility
    -0.08
    opo
    -0.07
    ÏĦική
    -0.07
    ×ķ×Ŀ
    -0.07
    éĺ»åĩ»æĪĺ
    -0.07
     itself
    -0.07
    IGE
    -0.07
    otence
    -0.07
    POSITIVE LOGITS
     jotka
    0.10
     коÑĤоÑĢÑĭе
    0.10
    коÑĤоÑĢÑĭе
    0.10
     alike
    0.09
     amelyek
    0.09
     themselves
    0.09
    encies
    0.09
    ×ķ׾×Ļ×Ŀ
    0.09
    å®ĥä»¬åľ¨
    0.09
     коÑĤоÑĢÑĭми
    0.09
    Activations Density 0.635%

    No Known Activations