© 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. 13953
    Prev
    Next
    INDEX
    Explanations

    here, again, question marks, periods

    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
    æ¦Ħ
    -0.09
    大ä¸įäºĨ
    -0.09
    _exports
    -0.08
    çĴĢ
    -0.08
    åĪĨåĪĨéĴŁ
    -0.08
    ä¾ĽæĤ¨
    -0.07
    /licenses
    -0.07
    æĭīå¾·
    -0.07
    .import
    -0.07
    igham
    -0.07
    POSITIVE LOGITS
    usercontent
    0.08
     Grat
    0.06
    åĩłæĹ¥
    0.06
    æľªåľ¨
    0.06
    aste
    0.06
     likely
    0.06
    çĤ¹åĩ»è¿Ľåħ¥
    0.06
    iatr
    0.06
    å±ħ士
    0.06
    ä¸Ģå®ļç¨ĭ度
    0.06
    Activations Density 0.140%

    No Known Activations