© 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. 15890
    Prev
    Next
    INDEX
    Explanations

    form of scaling behavior

    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
    å¼ķ以为
    -0.08
    å°Ķé¡¿
    -0.07
    dje
    -0.07
    éĤ£åı¯æĺ¯
    -0.07
    ajor
    -0.07
    ='-
    -0.07
    udi
    -0.07
    {@
    -0.07
    rt
    -0.07
    人åķĬ
    -0.07
    POSITIVE LOGITS
    å¾ħå®ļ
    0.10
    æľªçŁ¥
    0.10
     unknown
    0.10
    æľªçŁ¥çļĦ
    0.09
    _unknown
    0.08
    è¯ķæİ¢
    0.08
     descon
    0.08
     Unknown
    0.08
    unknown
    0.08
    Unknown
    0.07
    Activations Density 0.022%

    No Known Activations