© 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. 43707
    Prev
    Next
    INDEX
    Explanations

    random characters and numbers in links

    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
    ernels
    -0.07
    ettel
    -0.07
     inverted
    -0.06
    leen
    -0.06
    åľ¨å®¶
    -0.06
    çļĦä¸Ģå®ļ
    -0.06
    èݱåĿŀ
    -0.06
    åĽłäºº
    -0.06
     Ùħبت
    -0.06
    è°Ĭ
    -0.06
    POSITIVE LOGITS
     Khê
    0.08
    icke
    0.08
    éĥ½åľ¨è¿ĻéĩĮ
    0.07
    Ñģпали
    0.07
     коÑĤоÑĢомÑĥ
    0.07
    egó
    0.07
    ervised
    0.07
    à¹Ĥà¸Ħล
    0.07
    ListOf
    0.07
    å°±åľ¨è¿ĻéĩĮ
    0.07
    Activations Density 0.041%

    No Known Activations