© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44192
    Prev
    Next
    INDEX
    Explanations

    foot/farm/Floer

    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
    æijĨ
    -0.09
    lee
    -0.08
    lg
    -0.07
    eppe
    -0.07
    æijĨåľ¨
    -0.07
    abyrinth
    -0.07
    POSE
    -0.06
    ÙĪعة
    -0.06
    诬
    -0.06
    ä¾µçķ¥
    -0.06
    POSITIVE LOGITS
    åĪĨå·¦åı³
    0.08
    è±ĨåŃIJ
    0.07
    acket
    0.07
     isp
    0.07
    çĴĢ
    0.07
    AccountId
    0.07
    ids
    0.07
    /small
    0.07
    Incoming
    0.07
    emaine
    0.07
    Activations Density 0.001%

    No Known Activations