© 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. 56426
    Prev
    Next
    INDEX
    Explanations

    steric bulk and crowding

    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
    ernet
    -0.07
    éģĹçĹĩ
    -0.07
    å½Ĵå±ŀ
    -0.06
    年代åĪĿ
    -0.06
    æŬ
    -0.06
    agnet
    -0.06
     Pon
    -0.06
     Savage
    -0.06
    æģ¯
    -0.06
     Spells
    -0.06
    POSITIVE LOGITS
    زد
    0.08
     bulky
    0.08
     accessibility
    0.08
     surrounding
    0.07
    ç¨ĭ度ä¸Ĭ
    0.07
    ä¿®ç½Ĺ
    0.07
    éĴĿ
    0.07
    è´¹çİĩ
    0.07
    abee
    0.07
    修饰
    0.07
    Activations Density 0.004%

    No Known Activations