© 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. 33877
    Prev
    Next
    INDEX
    Explanations

    you can

    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
    æīįèĥ½ä½¿
    -0.07
    æīįèĥ½è®©
    -0.07
     pret
    -0.07
    尼奥
    -0.07
    ä¸įèĥ½è®©
    -0.06
    let
    -0.06
    è´
    -0.06
    emps
    -0.06
    令
    -0.06
    uken
    -0.06
    POSITIVE LOGITS
    ëŀĮ
    0.10
    iez
    0.09
     understands
    0.09
    à¸Ļำà¹Ħà¸Ľ
    0.08
    ç´įå¾Ĺ
    0.08
     understood
    0.08
     versteht
    0.08
     understand
    0.08
    åĸĥ
    0.08
    举ä¸Ģåıįä¸ī
    0.08
    Activations Density 0.041%

    No Known Activations