© 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. 42844
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
     Kern
    -0.07
    upati
    -0.07
    åį¡ç½Ĺ
    -0.07
    orni
    -0.07
    ç¦ıçĶ°
    -0.06
    zey
    -0.06
    fst
    -0.06
    izzatore
    -0.06
    à¸Ŀà¹īา
    -0.06
    hazi
    -0.06
    POSITIVE LOGITS
    æį¢ç®Ĺ
    0.09
    aw
    0.09
     expressed
    0.09
    converted
    0.08
     ang
    0.08
    æĬĺåIJĪ
    0.08
    Translated
    0.08
    Converted
    0.08
    encoded
    0.08
    express
    0.08
    Activations Density 0.213%

    No Known Activations