© 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. 42670
    Prev
    Next
    INDEX
    Explanations

    unpublished dispositions

    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
    å°±æĺ¯æĪijçļĦ
    -0.07
    æ¯Ķä½ł
    -0.07
    åĽ½æŃĮ
    -0.07
    ленÑĮ
    -0.07
    stand
    -0.07
    æłĩåĩĨåĴĮ
    -0.07
    åı·çłģ
    -0.07
    çī¹å°Ķ
    -0.07
    ê°ij
    -0.06
    ondo
    -0.06
    POSITIVE LOGITS
     ONLY
    0.09
     only
    0.08
    åĩ¡æĺ¯
    0.07
    ONLY
    0.07
    Only
    0.07
     certain
    0.07
    only
    0.07
     exclusively
    0.07
    .switch
    0.07
    ä¹Łåıª
    0.07
    Activations Density 0.025%

    No Known Activations