© 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. 24122
    Prev
    Next
    INDEX
    Explanations

    connect or connection to something

    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
    kinson
    -0.08
    erklärung
    -0.08
    -0.08
    manent
    -0.08
    ugin
    -0.08
    lette
    -0.08
    κÏģα
    -0.07
    iscal
    -0.07
    èī²åĪĹ
    -0.07
    ìį¨
    -0.07
    POSITIVE LOGITS
    ات
    0.10
    åľ¨ä¸Ģèµ·çļĦ
    0.10
    icut
    0.09
    nection
    0.09
    ivity
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    /link
    0.09
    sWith
    0.09
    encies
    0.08
    ings
    0.08
    Activations Density 0.064%

    No Known Activations