© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    number of

    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
     Embedded
    -0.08
     embedded
    -0.08
    Embedded
    -0.07
    à¹ĥà¸Ļà¸ķัว
    -0.07
    为éļ¾
    -0.07
    embedded
    -0.07
    èĦ±
    -0.07
     embed
    -0.06
    dev
    -0.06
    çļĦèĩªçĶ±
    -0.06
    POSITIVE LOGITS
     instead
    0.09
     shallow
    0.09
     rather
    0.09
     low
    0.09
    æĺ¯å¾Īå¤ļ
    0.09
    ä¸įæ±Ĥ
    0.08
    å¯ĨéĽĨåŀĭ
    0.08
    å°ıèĢĮ
    0.08
    åįķ次
    0.08
     بدÙĦاÙĭ
    0.08
    Activations Density 0.109%

    No Known Activations