© 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. 31597
    Prev
    Next
    INDEX
    Explanations

    exactly (quantifiers)

    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
    ä¹īè¯į
    -0.06
    ampa
    -0.06
    æİ¥
    -0.06
     Eink
    -0.06
    erral
    -0.06
    èıľçļĦ
    -0.06
     gieo
    -0.06
    ierzch
    -0.06
    lette
    -0.06
    åģļåĪ°
    -0.06
    POSITIVE LOGITS
    Identity
    0.08
    ighted
    0.08
    opportun
    0.08
    indexed
    0.07
    esty
    0.07
    ipay
    0.07
    IPAddress
    0.07
    -bin
    0.07
    çĭ¸
    0.07
    ulé
    0.07
    Activations Density 0.006%

    No Known Activations