© 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. 55470
    Prev
    Next
    INDEX
    Explanations

    US states and abbreviations

    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
    feit
    -0.08
     Ñģобой
    -0.07
    åIJ¦
    -0.07
    ä¸į失
    -0.07
    æĪĸéĥ¨åĪĨ
    -0.07
    æĮģä¹ĭ以
    -0.07
    oin
    -0.07
    æĪ¿åľ°
    -0.07
    ัà¸ģษà¹Į
    -0.07
    wn
    -0.06
    POSITIVE LOGITS
    åĴĮä¸Ĭæµ·
    0.08
    egov
    0.07
    ç»Ļ大家åĪĨ享
    0.07
    iculum
    0.07
    å®ľäºº
    0.07
     Sunshine
    0.07
    icola
    0.06
     Utara
    0.06
    å·ŀçļĦ
    0.06
    BITS
    0.06
    Activations Density 0.245%

    No Known Activations