© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    sentence start after punctuation

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    quisite
    -0.06
    Occurred
    -0.06
    缸åħ³éĹ®çŃĶ
    -0.06
    âĢ¦
    -0.06
    æķ
    -0.06
    à¸Ńัà¸Ļ
    -0.06
     ord
    -0.06
    æĪijåĴĮæĪijçļĦ
    -0.06
    hana
    -0.06
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.09
    åħ¶æ¬¡æĺ¯
    0.09
    åħ¶æ¬¡
    0.08
    æķ¢è¯´
    0.07
    åħ¶äºĮ
    0.07
    äºĮæĿ¥
    0.07
     inoltre
    0.07
    OCR
    0.07
    ebr
    0.07
    oges
    0.07
    Activations Density 0.151%

    No Known Activations