© 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. 9811
    Prev
    Next
    INDEX
    Explanations

    as above, same as, or usual

    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
    æļĤå®ļ
    -0.07
    çľĭæĿ¥
    -0.07
    åı¹
    -0.07
    ador
    -0.07
    ingu
    -0.07
    sey
    -0.06
    ỡ
    -0.06
    ativi
    -0.06
    æĬµæĬĹ
    -0.06
    ç®Ģ称
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.11
     except
    0.10
    ä¸Ĭè¿°
    0.10
    åīįè¿°
    0.09
    except
    0.09
     aforementioned
    0.09
    mentioned
    0.09
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    åIJĮæ§ĺ
    0.08
    dden
    0.08
    Activations Density 0.173%

    No Known Activations