© 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. 43229
    Prev
    Next
    INDEX
    Explanations

    agreeing by action

    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
    ÑĢаÑĨиÑı
    -0.07
    ease
    -0.07
    è°ģä¹Ł
    -0.07
    .Verify
    -0.07
    ä¸Ń表示
    -0.06
    ctrine
    -0.06
    å¦ĤæŀľéģĩåĪ°
    -0.06
    вÑĸв
    -0.06
    æĺĵçĪĨ
    -0.06
    iloc
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.09
     contrário
    0.09
    ,this
    0.08
     contrast
    0.08
    ä¸įèµ·
    0.07
     ìĤ¬ìļ©íķĺë©´
    0.07
    è¿Ļä¸ĢçĤ¹
    0.07
    è¿ĻäºĽä¿¡æģ¯
    0.07
    ignano
    0.07
     itulah
    0.07
    Activations Density 0.059%

    No Known Activations