© 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. 49130
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    å¾ĭå·±
    -0.07
    ');"
    -0.06
    uilt
    -0.06
    ä¸ĭåIJĮ
    -0.06
    æľ¯
    -0.06
    <|box_end|>
    -0.06
     separ
    -0.06
     Fron
    -0.06
    ä¸įäºĨå¤ļä¹ħ
    -0.06
    Ỽm
    -0.05
    POSITIVE LOGITS
    æŀĹéĢ¸
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.07
    æĶ¾æĿ¾å¿ĥæĥħ
    0.07
    åĩŃçĿĢ
    0.07
    éķ·çļĦ
    0.07
    <Component
    0.07
    ÙĪÙħات
    0.07
    mert
    0.07
    aéroport
    0.07
    нÑij
    0.07
    Activations Density 0.122%

    No Known Activations