© 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. 21002
    Prev
    Next
    INDEX
    Explanations

    sorting elements last or at the end

    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
    ALI
    -0.09
    olls
    -0.09
    åį«ä¸ľ
    -0.08
    lý
    -0.08
    scopes
    -0.08
    saus
    -0.08
    volt
    -0.08
    TRACT
    -0.07
    ANDA
    -0.07
    人èĥ½
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.09
     sorted
    0.08
     sort
    0.08
     reorder
    0.08
     occupy
    0.08
     Sort
    0.08
    .sort
    0.08
    æİĴ
    0.07
    åIJ«
    0.07
    æİĴåĪĹ
    0.07
    Activations Density 0.022%

    No Known Activations