© 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. 23689
    Prev
    Next
    INDEX
    Explanations

    film, album, song, play, restaurant, name, magazine, India, revolt

    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
    人å¤ļ
    -0.07
    olly
    -0.07
    ä½³èĬĤ
    -0.07
    делки
    -0.07
    elly
    -0.07
     Leban
    -0.07
    eco
    -0.07
    igli
    -0.07
    unas
    -0.07
    UGH
    -0.06
    POSITIVE LOGITS
     wikipedia
    0.10
    âĢİ
    0.10
    {{{
    0.09
     Wikipedia
    0.09
     âĢİ
    0.08
    {{
    0.08
     wiki
    0.07
    iminal
    0.07
     prot
    0.07
    ä¹ĭæŃ»
    0.07
    Activations Density 1.215%

    No Known Activations