© 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. 51194
    Prev
    Next
    INDEX
    Explanations

    numbers in legal documents or lists

    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
    ilers
    -0.08
    eren
    -0.07
    erma
    -0.07
    crc
    -0.07
    ILER
    -0.07
    illus
    -0.07
     Här
    -0.07
    usa
    -0.06
    urette
    -0.06
    ndx
    -0.06
    POSITIVE LOGITS
    å°ĶèĴĻ
    0.09
    abee
    0.08
    egral
    0.07
    edral
    0.07
    antage
    0.07
    è¶ģ
    0.07
    请ä¸İæĪij们èģĶç³»
    0.07
    çİ°
    0.07
    械
    0.07
    ê¼Ń
    0.07
    Activations Density 0.002%

    No Known Activations