© 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. 47143
    Prev
    Next
    INDEX
    Explanations

    linear gradient CSS and SVG

    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
    impa
    -0.06
    ht
    -0.06
    idere
    -0.06
    æ´»
    -0.06
    çĤ¹æѤ
    -0.06
    ä¸īå°º
    -0.06
    oj
    -0.05
    è®°å¾Ĺ
    -0.05
     жив
    -0.05
     thuis
    -0.05
    POSITIVE LOGITS
    IVO
    0.08
    룴
    0.08
     datastore
    0.08
    ableView
    0.08
    agate
    0.08
    eges
    0.08
     ÄijÃł
    0.08
    æĸĩ稿
    0.08
    ISA
    0.08
    iola
    0.08
    Activations Density 0.001%

    No Known Activations