© 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. 50245
    Prev
    Next
    INDEX
    Explanations

    escape sequences and functions

    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
    entifier
    -0.09
    cule
    -0.09
    UMMY
    -0.08
    erness
    -0.08
    ièrement
    -0.08
    puter
    -0.08
    ¸
    -0.08
    edly
    -0.08
    ÑĪенко
    -0.08
     timespec
    -0.08
    POSITIVE LOGITS
    ãģµãģĨãģ«
    0.09
    èĪ¬åľ°
    0.07
    fully
    0.07
    ylon
    0.07
    el
    0.06
    é«ĺ溫
    0.06
    สà¹Į
    0.06
    Ĺ
    0.06
     hãi
    0.06
    féle
    0.06
    Activations Density 0.129%

    No Known Activations