© 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. 8760
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
    ä¼¼æĺ¯
    -0.07
    ä¸Ĭè¡Ĺ
    -0.07
    èľľ
    -0.07
     ÙĪØ¥ÙĨÙħا
    -0.07
    æĭĽæĥ¹
    -0.07
    irim
    -0.06
    çĪ±ä¸Ĭ
    -0.06
     into
    -0.06
    ovol
    -0.06
     Into
    -0.06
    POSITIVE LOGITS
    并对åħ¶
    0.09
    plet
    0.08
    并ä»İ
    0.08
    并
    0.08
    åį´åıijçİ°
    0.07
    并å¼Ģå§ĭ
    0.07
    oug
    0.07
    å¹¶è¿Ľè¡Į
    0.07
    并æĮī
    0.07
    æīįåıijçİ°
    0.07
    Activations Density 0.235%

    No Known Activations