© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    advancements and prestigious technology

    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
     obvious
    -0.08
     résumé
    -0.08
     anyway
    -0.07
     toward
    -0.07
     bila
    -0.07
     (“
    -0.07
     kinds
    -0.07
     probably
    -0.07
     biç
    -0.07
     “
    -0.07
    POSITIVE LOGITS
     advancements
    0.10
     delve
    0.09
    ...\
    0.08
    æĺĵè´Ń
    0.08
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.08
    cione
    0.07
     [âĢ¦
    0.07
     **'
    0.07
     esteemed
    0.07
     noqa
    0.07
    Activations Density 0.030%

    No Known Activations