© 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. 2121
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
     Stro
    -0.07
    ild
    -0.07
     quarti
    -0.07
    ÃŃculas
    -0.06
    jed
    -0.06
    æŀĹåŃIJ
    -0.06
    put
    -0.06
    enea
    -0.06
     Kong
    -0.06
     اÙĦإس
    -0.06
    POSITIVE LOGITS
    åħŃç§į
    0.12
    åħŃ大
    0.11
    åħŃ个
    0.11
    åħŃæĺ¯
    0.10
    ä¸ĥ个
    0.10
    ষà§įà¦ł
    0.10
    åħŃ
    0.09
    -six
    0.09
    åħŃä½į
    0.09
    หà¸ģ
    0.09
    Activations Density 0.352%

    No Known Activations