© 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. 26889
    Prev
    Next
    INDEX
    Explanations

    scalar operations and identifiers

    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
     pat
    -0.07
    обоÑĢоÑĤ
    -0.07
    çĶŁæ´»ä¹łæĥ¯
    -0.07
    éĹ²
    -0.07
    Stamped
    -0.07
    iben
    -0.07
     Pat
    -0.06
    éĸij
    -0.06
    Æ¡i
    -0.06
     Patt
    -0.06
    POSITIVE LOGITS
     scalar
    0.09
     extracted
    0.08
    个ä½ĵ
    0.08
    Extract
    0.08
     Extract
    0.08
    Scalar
    0.08
     Scalar
    0.08
    _scalar
    0.07
    scalar
    0.07
    æıIJåıĸ
    0.07
    Activations Density 0.088%

    No Known Activations