© 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. 61468
    Prev
    Next
    INDEX
    Explanations

    chemical naming conventions

    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
    ëŀ
    -0.07
    geries
    -0.07
    åĩºçİ°è¿ĩ
    -0.07
    æĺ¯ä¸įå¤Ł
    -0.07
    æk
    -0.07
    urat
    -0.07
    å¾Ĺè¦ģ
    -0.07
    æĤĦæĤĦ
    -0.07
    bidden
    -0.06
     ?:
    -0.06
    POSITIVE LOGITS
    opin
    0.08
    alen
    0.07
    æĥĬéŃĤ
    0.07
    ä¿¡æģ¯æĺ¾ç¤º
    0.07
    å®ĺ
    0.07
    å±Ĭåħ¨åĽ½
    0.07
    ÅŁa
    0.07
    åĩĿå¿ĥ
    0.06
    )(((
    0.06
    ylan
    0.06
    Activations Density 0.048%

    No Known Activations