© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
    istique
    -0.08
    äºĨåľ¨
    -0.07
    à®ļà¯įà®ļ
    -0.07
    emming
    -0.06
    åľ°å¸¦
    -0.06
    ãģ¾ãģł
    -0.06
    大åIJį
    -0.06
    eh
    -0.06
    ostro
    -0.06
    PathVariable
    -0.06
    POSITIVE LOGITS
    erei
    0.09
    à¸Ļà¹Į
    0.08
    icza
    0.08
    ftware
    0.08
    resden
    0.07
    erry
    0.07
    erawat
    0.07
    幸è¿IJçļĦ
    0.07
    รà¹Į
    0.07
    erweise
    0.07
    Activations Density 0.388%

    No Known Activations