© 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. 28843
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    sez
    -0.08
    åŁ¹
    -0.08
    äºİä¸Ģ
    -0.07
    ajs
    -0.07
    ceo
    -0.07
    ัà¹Īà¸ĩ
    -0.07
    ä¿¡å°ģ
    -0.07
     jota
    -0.07
    sitemap
    -0.07
    getDefault
    -0.07
    POSITIVE LOGITS
    ç¡®å®ļ为
    0.08
    åѤ
    0.07
     onwards
    0.07
    为å¥ijæľº
    0.06
    ë²Ī
    0.06
     baÅŁlayan
    0.06
    ches
    0.06
    amente
    0.06
     origin
    0.06
    ä¹ĭä¸ĢçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations