© 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. 28881
    Prev
    Next
    INDEX
    Explanations

    return code paths

    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
    iest
    -0.08
    èĬĤçļĦ
    -0.07
    ='',
    -0.07
     Cian
    -0.07
    ='${
    -0.07
    ='_
    -0.07
    縼
    -0.07
    DIR
    -0.06
    ÄĻ
    -0.06
    sst
    -0.06
    POSITIVE LOGITS
         ↵↵
    0.08
    ↵↵
    0.08
           ↵↵
    0.08
        ↵↵
    0.08
            ↵↵
    0.07
          ↵↵
    0.07
     ↵↵
    0.07
                ↵↵
    0.07
    ç¾Ĭ
    0.07
    ané
    0.06
    Activations Density 0.013%

    No Known Activations