© 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. 55479
    Prev
    Next
    INDEX
    Explanations

    physical and spatial dimensions

    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
    _THRESHOLD
    -0.08
    etri
    -0.07
    uml
    -0.07
    agre
    -0.07
    ipse
    -0.06
    itarian
    -0.06
    elper
    -0.06
    ÑĢÑĤа
    -0.06
    ä¸Ģæ´¾
    -0.06
    agoon
    -0.06
    POSITIVE LOGITS
    维度
    0.08
    åĴĮæĶ¿æ²»
    0.08
    éĻĦçĿĢ
    0.08
     dimension
    0.07
     Hil
    0.07
     Fold
    0.07
    åĴĮæŶéĹ´
    0.07
    iras
    0.07
    æĹłåħ³
    0.07
     attached
    0.07
    Activations Density 0.006%

    No Known Activations