© 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. 18314
    Prev
    Next
    INDEX
    Explanations

    class inheritance

    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
    urig
    -0.08
    idar
    -0.07
    blatt
    -0.07
    åĨħå¿ĥä¸ĸçķĮ
    -0.07
    ä¸ĢåĪ°
    -0.07
     Redistributions
    -0.06
    æĹ¥åĪ°
    -0.06
    ignano
    -0.06
    ä¸įæħİ
    -0.06
    缸åħ³æݨèįIJ
    -0.06
    POSITIVE LOGITS
    icom
    0.08
    ingleton
    0.07
    æĻ®éĢļçļĦ
    0.07
     StObject
    0.07
    ึà¹Īà¸ĩ
    0.07
    åŁºç¡ĢçļĦ
    0.07
    äºĨä¸ĢèĪ¬
    0.07
    WithTitle
    0.07
    /base
    0.07
    -base
    0.07
    Activations Density 0.199%

    No Known Activations