© 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. 18479
    Prev
    Next
    INDEX
    Explanations

    sigma followed by 1

    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
    ÑĥÑĢе
    -0.06
    æѦéĻµ
    -0.06
    èĩªæݧ
    -0.06
    è¿Ļé¢Ĺ
    -0.06
     nomin
    -0.06
     Afr
    -0.06
    æľŁéĻIJåĨħ
    -0.06
    iesa
    -0.06
     explo
    -0.06
    echt
    -0.06
    POSITIVE LOGITS
    鸡èħ¿
    0.08
    _hooks
    0.08
    LOOK
    0.08
    structor
    0.07
    .define
    0.07
    天éŃĶ
    0.07
     Armour
    0.07
    à¸Ĺัà¸ŀ
    0.07
    éľ
    0.07
    çĸ«æĥħéĺ²æݧåĴĮ
    0.07
    Activations Density 0.001%

    No Known Activations