© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13985
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by words

    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
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.06
     hâm
    -0.06
    agi
    -0.06
     Sah
    -0.06
    åĽ¾èħ¾
    -0.06
    Ñīе
    -0.06
     Tand
    -0.06
    schau
    -0.06
    称ä¹ĭ为
    -0.06
    æĹłç©·çļĦ
    -0.06
    POSITIVE LOGITS
    antum
    0.08
    olato
    0.08
    neze
    0.08
    nees
    0.08
    urette
    0.07
    ensible
    0.07
    steen
    0.07
     nauw
    0.07
    ä¸ĥéĩĮ
    0.07
     bure
    0.07
    Activations Density 0.002%

    No Known Activations