© 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. 33904
    Prev
    Next
    INDEX
    Explanations

    currencies, lists, six pigs, memory

    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
    秸
    -0.07
    ä»
    -0.07
    ×Ļ×Ļ
    -0.06
    åį¸
    -0.06
    æį¨
    -0.06
    idou
    -0.06
    reté
    -0.06
    夫妻åħ±åIJĮ
    -0.06
    édé
    -0.06
    à°ªà±ģ
    -0.06
    POSITIVE LOGITS
    -track
    0.08
    cik
    0.08
     separately
    0.08
     trackers
    0.08
    çİĭ大
    0.07
    Term
    0.07
    æķ°æį®ç»Łè®¡
    0.07
    atform
    0.07
    cene
    0.07
    æĴĴ
    0.07
    Activations Density 0.004%

    No Known Activations