© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64132
    Prev
    Next
    INDEX
    Explanations

    lists often followed by code or sentence beginnings

    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
    inha
    -0.08
     casse
    -0.08
    ÑħаÑĤÑĮ
    -0.07
    ollen
    -0.07
    umbing
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    å®ĺæĸ¹å¾®ä¿¡
    -0.07
    ienz
    -0.06
    æĻĤåĢĻ
    -0.06
    ambi
    -0.06
    POSITIVE LOGITS
    omot
    0.09
    etros
    0.08
    Sim
    0.07
    ë°ľìłĦ
    0.07
    ä¸ŃæĪIJéķ¿
    0.07
    踪迹
    0.07
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    0.07
    è¿Ľåħ¥
    0.07
     Sim
    0.06
     forts
    0.06
    Activations Density 0.095%

    No Known Activations