© 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. 9988
    Prev
    Next
    INDEX
    Explanations

    historical figures and algorithms

    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
    åĪĢåŃIJ
    -0.09
     Klassen
    -0.08
    _ONCE
    -0.08
    -options
    -0.08
    åħļçļĦåįģä¹Ŀå±Ĭ
    -0.08
    åĭ¤åĭ¤æģ³æģ³
    -0.08
    ×ij×Ĺ
    -0.08
    Jackson
    -0.08
    è¯Ŀåī§
    -0.08
    -lang
    -0.08
    POSITIVE LOGITS
     centuries
    0.08
    åı¤èĢģçļĦ
    0.07
    åı¤èĢģ
    0.07
    ä¸İçݰ代
    0.07
    ian
    0.07
     ancient
    0.07
    0.07
     medieval
    0.07
    سط
    0.07
    reis
    0.07
    Activations Density 0.016%

    No Known Activations