© 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. 49630
    Prev
    Next
    INDEX
    Explanations

    my writings and projects

    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
    æ¯ĶæĪij们
    -0.10
    æĺİæĺİ
    -0.09
    åijĬè¯īæĪij们
    -0.08
    給æĪijåĢij
    -0.08
     sophisticated
    -0.08
     عاÙĦÛĮ
    -0.08
     brilliantly
    -0.08
     ÐłÐµÐºÐ¾Ð¼ÐµÐ½Ð´Ñĥем
    -0.08
     bijak
    -0.08
    对æĪij们çļĦ
    -0.08
    POSITIVE LOGITS
    æĭĻ
    0.11
    æĪijçļĦå·¥ä½ľ
    0.10
     myself
    0.10
     modest
    0.10
     attempt
    0.09
     attempts
    0.09
     hopefully
    0.09
    å°Ŀè¯ķ
    0.09
    å°½éĩı
    0.09
    åĬĽæ±Ĥ
    0.09
    Activations Density 0.923%

    No Known Activations