© 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. 64538
    Prev
    Next
    INDEX
    Explanations

    e.g. such as

    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
     Äijâu
    -0.08
    æŨ
    -0.07
    gis
    -0.07
    envir
    -0.07
    ׼×ķף
    -0.07
     Nun
    -0.07
     Pej
    -0.07
    opan
    -0.06
    eyed
    -0.06
    ega
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.11
     halnya
    0.09
    amment
    0.08
    @m
    0.07
    ä¾ĭåŃIJ
    0.07
    ¤
    0.07
    à¹Ģà¸Ķียว
    0.07
     ìĺĪ를
    0.07
    vrier
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
    Activations Density 0.217%

    No Known Activations