© 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. 64963
    Prev
    Next
    INDEX
    Explanations

    RT followed by numbers/symbols

    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
    ekut
    -0.09
    oooooooo
    -0.09
    akest
    -0.08
    jist
    -0.08
    heiz
    -0.08
    æĮijé£Ł
    -0.08
    lina
    -0.08
    eté
    -0.08
    Æ°á»Ŀi
    -0.08
    -Sah
    -0.08
    POSITIVE LOGITS
    ing
    0.06
    our
    0.06
    æľŁ
    0.06
    æ¦Ĥ
    0.06
    aque
    0.06
    аем
    0.06
    a
    0.06
    آخر
    0.06
    ender
    0.06
    t
    0.06
    Activations Density 0.002%

    No Known Activations