© 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. 19875
    Prev
    Next
    INDEX
    Explanations

    e.g

    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
    ÑģÑı
    -0.12
    Ùĩ
    -0.10
    er
    -0.09
    ÛĮ
    -0.09
    ÙĦ
    -0.08
    ÙĬØ©
    -0.08
    åĴĮ
    -0.08
    ب
    -0.08
    es
    -0.08
    zir
    -0.08
    POSITIVE LOGITS
    Ķ
    0.09
    urement
    0.09
    .,
    0.09
    orgen
    0.08
    Ł
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    تÙħاÙĨ
    0.08
    -services
    0.08
    ÙİØ«
    0.08
    çİĩè¾¾åĪ°
    0.07
    Activations Density 0.021%

    No Known Activations