© 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. 49594
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
    åĨįä¸į
    -0.08
    vand
    -0.08
    à§į
    -0.08
    antik
    -0.08
    ulon
    -0.08
    łĢ
    -0.08
    æĦŁæ¿Ģ
    -0.08
    èĢĮéĻį
    -0.07
     ái
    -0.07
    è¿Ļä¹Ī大
    -0.07
    POSITIVE LOGITS
     citation
    0.06
     numbers
    0.06
    天å¤ĸ
    0.06
    èij©
    0.06
     §§
    0.06
     numbered
    0.06
    ort
    0.06
    æ´»åĬ¨çŃī
    0.06
     cites
    0.06
    为æķ°
    0.06
    Activations Density 0.029%

    No Known Activations