© 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. 43201
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    ilo
    -0.07
    lein
    -0.06
    vain
    -0.06
    tn
    -0.06
     concurrent
    -0.06
     Werb
    -0.06
    zano
    -0.06
     напÑĢ
    -0.06
    ç»Ħè¯į
    -0.06
    ızı
    -0.06
    POSITIVE LOGITS
    ellig
    0.08
    æŁIJç§į
    0.08
    æŁIJæŁIJ
    0.08
    æŁIJ个
    0.08
    ÄĽk
    0.08
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    0.08
    æŃĩå°Ķ
    0.07
    æŁIJ
    0.07
     некоÑĤоÑĢ
    0.07
    åĪĻçĶ±
    0.07
    Activations Density 0.012%

    No Known Activations