© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23195
    Prev
    Next
    INDEX
    Explanations

    digits and "each meal"

    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
    å¼ķéĩı
    -0.08
    кеÑĢ
    -0.08
    emor
    -0.07
    çķ³
    -0.07
    kers
    -0.07
    广åıij
    -0.07
    tijk
    -0.07
    ($)
    -0.07
    _SANITIZE
    -0.07
     –**
    -0.07
    POSITIVE LOGITS
    اء
    0.07
    sic
    0.07
    orr
    0.06
    oyo
    0.06
    irr
    0.06
    Touches
    0.06
    ฤ
    0.06
    oshi
    0.06
     تبع
    0.06
    é¾Ħ
    0.06
    Activations Density 0.024%

    No Known Activations