© 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. 58211
    Prev
    Next
    INDEX
    Explanations

    I’ve been

    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
    */,
    -0.08
    REATE
    -0.07
     <=
    -0.07
    .ht
    -0.07
     *"
    -0.07
     "
    -0.07
     <*
    -0.07
    ne
    -0.07
    ãĥ¼ãĤ¸ãĥ£
    -0.07
    ookies
    -0.07
    POSITIVE LOGITS
    âĢij
    0.10
      ↵↵
    0.09
    æīĵ人
    0.08
    âĢ
    0.07
      ↵
    0.07
    ’)
    0.07
    ’Brien
    0.06
     khảo
    0.06
     ↵↵
    0.06
    åĴļåĴļ
    0.06
    Activations Density 0.164%

    No Known Activations