© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    Facel Vega, choroid, Blountville, St. Vincent, Listener, default HP, PB, phase

    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
    suming
    -0.07
    /devices
    -0.06
    ovid
    -0.06
     ((!
    -0.06
    [âĢ¦
    -0.06
    åĪ¶è£ģ
    -0.06
    inces
    -0.06
    çīµæī¯
    -0.06
    elter
    -0.06
     Gelt
    -0.05
    POSITIVE LOGITS
    +xml
    0.09
    èĢĥè¯ķé¢ĺåºĵ
    0.08
    为éĩįçĤ¹
    0.07
    á»iji
    0.07
    legg
    0.07
     ÙĪآخر
    0.07
    á»ijng
    0.07
    è«
    0.07
    éļª
    0.07
    _cur
    0.07
    Activations Density 0.092%

    No Known Activations