© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma or period

    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
    åłķ
    -0.06
    abo
    -0.06
    -s
    -0.06
    åĬ³
    -0.06
    esco
    -0.06
    ================================================================
    -0.06
    usta
    -0.06
    åĤį
    -0.06
    åŃļ
    -0.06
    ...).
    -0.06
    POSITIVE LOGITS
    utang
    0.08
    oref
    0.08
    educt
    0.08
    endan
    0.08
    ä½łåij¢
    0.08
     htons
    0.08
    åĩĢé¢Ŀ
    0.08
    ationToken
    0.08
    úÄį
    0.08
    çĤ¹è¿ĻéĩĮ
    0.07
    Activations Density 0.002%

    No Known Activations