© 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. 12939
    Prev
    Next
    INDEX
    Explanations

    your question

    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
     Strict
    -0.08
    colo
    -0.07
    æľ¬æĬ¥åijĬ
    -0.07
    Strict
    -0.07
     strictly
    -0.06
    strict
    -0.06
     terg
    -0.06
    ä»»ä½ł
    -0.06
    æľ¬ç«ĻåĨħ容
    -0.06
     proper
    -0.06
    POSITIVE LOGITS
    ãģ£ãģĹãĤĥ
    0.08
    reland
    0.08
    ested
    0.07
    åħ³äºİåĬłå¼º
    0.07
    ãģ®ãĤĪãģĨãģª
    0.07
    -described
    0.07
    صÙĬد
    0.07
    ãĤĪãģĨãģª
    0.07
     ë§IJìĶĢ
    0.07
     اÙĦÙĥرÙĬÙħ
    0.07
    Activations Density 0.052%

    No Known Activations