© 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. 7593
    Prev
    Next
    INDEX
    Explanations

    double, two, couples, folded

    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
    æ··æĿĤ
    -0.09
    aub
    -0.08
    æ··åIJĪ
    -0.08
    åįĥ
    -0.08
    elang
    -0.08
    à¹Īà¸Ńà¸Ļ
    -0.08
    plug
    -0.07
    ç¹°
    -0.07
    Sortable
    -0.07
    è¶Ĭ
    -0.07
    POSITIVE LOGITS
     doubled
    0.16
    åıĮåĢį
    0.15
    åĬłåĢį
    0.15
     doubling
    0.14
     doubles
    0.14
     double
    0.13
    两åĢį
    0.12
    ç¿»åĢį
    0.12
    ä¸ĢåĢį
    0.12
    åıĮè¾¹
    0.12
    Activations Density 0.020%

    No Known Activations