© 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. 57944
    Prev
    Next
    INDEX
    Explanations

    advantages of

    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
    å¿ħè¦ģ
    -0.07
    èĭ¥å¹²
    -0.07
    ×ĵר
    -0.07
    byn
    -0.06
    ä»Ģä¹ĪæĦıæĢĿ
    -0.06
     mehreren
    -0.06
    éĩįè¦ģ
    -0.06
    alama
    -0.06
    ×Ĺ×ķ
    -0.06
    éľĢçĶ¨
    -0.06
    POSITIVE LOGITS
    racht
    0.09
     takiego
    0.08
     ÑĤакого
    0.08
    æѤç§į
    0.08
    缸æ¯Ķäºİ
    0.08
     данного
    0.08
    äºĨè¿Ļ个
    0.07
    _queues
    0.07
     αÏħÏĦοÏį
    0.07
    缸è¾ĥäºİ
    0.07
    Activations Density 0.369%

    No Known Activations