© 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. 16550
    Prev
    Next
    INDEX
    Explanations

    ok, alright, thanks

    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
    ãģĦãģ¾ãģĽãĤĵãģĭ
    -0.07
     confront
    -0.07
    )":
    -0.07
    )':
    -0.07
    ?):
    -0.07
    æĸŁéħĮ
    -0.07
    æĺ¯åIJ¦æŃ£å¸¸
    -0.06
    ãģĦãģĭãģĮ
    -0.06
    ãĥīãĥ©
    -0.06
     ?",
    -0.06
    POSITIVE LOGITS
    æĪijä¹Łåİ»
    0.08
    ä¸įè¿ĩè¿Ļ
    0.08
    дем
    0.08
    дей
    0.08
    blr
    0.07
    æĹłå¼Ĥè®®
    0.07
    éĵĤéĩij
    0.07
    çIJĽ
    0.07
    à¹ĩà¸Ķ
    0.07
    boro
    0.07
    Activations Density 0.099%

    No Known Activations