© 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. 45063
    Prev
    Next
    INDEX
    Explanations

    special characters and math symbols

    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
     []).
    -0.07
    ulous
    -0.07
    warts
    -0.07
    noc
    -0.07
    elop
    -0.07
    +)\
    -0.07
    enet
    -0.07
    úi
    -0.07
    `\
    -0.06
    åŀĭåĴĮ
    -0.06
    POSITIVE LOGITS
    essar
    0.08
    essin
    0.06
     Tbk
    0.06
    çĶļèĩ³è¿ĺæľī
    0.06
    weiler
    0.06
    atever
    0.06
     sore
    0.06
     etc
    0.06
    缸ç»ĵåIJĪ
    0.06
    殿ä¸ĭ
    0.06
    Activations Density 0.002%

    No Known Activations