© 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. 15404
    Prev
    Next
    INDEX
    Explanations

    overt frequencies, multiples, doubling

    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
    æĨ¾
    -0.08
    ä¿¡è¾¾
    -0.07
    è¿ĺæľīä¸ĢçĤ¹
    -0.07
    imits
    -0.07
    licted
    -0.07
    rä
    -0.07
    Äįiu
    -0.07
     Fus
    -0.07
    asted
    -0.07
     bios
    -0.06
    POSITIVE LOGITS
    åĢįæķ°
    0.09
    åĴĮ第
    0.08
    åĢį
    0.08
    ä¾Ŀ次
    0.08
     multiples
    0.08
    èĭŁ
    0.08
    ä¾Ŀ次为
    0.07
     doubling
    0.07
    reuse
    0.07
    loth
    0.07
    Activations Density 0.002%

    No Known Activations