© 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. 10070
    Prev
    Next
    INDEX
    Explanations

    parliamentary commission president-designate

    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
    ucie
    -0.07
    æĹ¶ä¸º
    -0.07
    endus
    -0.06
    è¡¡éĺ³
    -0.06
    odore
    -0.06
    éľ²å¤´
    -0.06
    ugg
    -0.06
    ä¸įè¦ģåĽłä¸º
    -0.06
     panc
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
    POSITIVE LOGITS
    âĢij
    0.08
    åľ¨ä¸Ĭè¿°
    0.07
    åijĥ
    0.07
     versus
    0.07
    MT
    0.07
    ]|[
    0.06
    yson
    0.06
    å±ħéħĴå±ĭ
    0.06
    çijŀæĭī
    0.06
    ))?
    0.06
    Activations Density 0.033%

    No Known Activations