© 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. 51311
    Prev
    Next
    INDEX
    Explanations

    archaeological sites, tools, and camps

    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
    è°ļ
    -0.06
    ç¹
    -0.06
     pend
    -0.06
    设æ³ķ
    -0.06
     Pois
    -0.06
     Sind
    -0.06
    adam
    -0.06
    åĵī
    -0.06
    rang
    -0.05
     conc
    -0.05
    POSITIVE LOGITS
    åĩºåľŁ
    0.12
     archae
    0.12
     archaeological
    0.12
     Archae
    0.11
    æĻļæľŁ
    0.11
     dated
    0.10
    å¢ĵèij¬
    0.10
    æĶ¶èĹıæľ¬ç«Ļ
    0.10
     excav
    0.10
    èĢĥåı¤
    0.10
    Activations Density 0.121%

    No Known Activations