© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23397
    Prev
    Next
    INDEX
    Explanations

    shape and its properties

    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
     возÑĢаÑģÑĤа
    -0.08
    æŁ¬
    -0.07
    äºĭéłħ
    -0.07
    çĹħæĥħæııè¿°
    -0.07
    æĥħåĨµæĿ¥çľĭ
    -0.07
     warta
    -0.07
    spro
    -0.07
    ียà¸ĩ
    -0.07
     tá»ij
    -0.07
    é¢ĿçļĦ
    -0.07
    POSITIVE LOGITS
    (shape
    0.11
    å½¢çĬ¶
    0.11
    shape
    0.10
     shape
    0.10
    åIJĦå¼Ĥ
    0.10
     Shape
    0.10
    å½¢çĬ¶çļĦ
    0.10
     shapes
    0.09
    Shape
    0.09
    åĴĮåĨħ容
    0.09
    Activations Density 0.066%

    No Known Activations