© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50117
    Prev
    Next
    INDEX
    Explanations

    questions or explanations

    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
    oros
    -0.09
    ouro
    -0.08
     whichever
    -0.08
    puty
    -0.08
    azit
    -0.08
    OnChange
    -0.07
     zorg
    -0.07
     compro
    -0.07
     whatever
    -0.07
    注æĦıçļĦæĺ¯
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.14
     ÙĪÙĥÙĬÙģ
    0.09
    为æѤ
    0.09
    以åıĬåľ¨
    0.09
    以åıĬ
    0.09
    以åıĬ缸åħ³
    0.08
    /how
    0.08
     ÙĪÙĩÙĦ
    0.08
    以åıĬ对
    0.07
    VRT
    0.07
    Activations Density 0.208%

    No Known Activations