© 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. 15499
    Prev
    Next
    INDEX
    Explanations

    version 3

    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
    roit
    -0.09
    azah
    -0.08
    verture
    -0.08
    lage
    -0.08
    -thirds
    -0.08
    UGIN
    -0.08
    jenigen
    -0.08
    sworth
    -0.07
    à§įস
    -0.07
    خابرات
    -0.07
    POSITIVE LOGITS
    rd
    0.16
    -quarters
    0.13
    .amazonaws
    0.11
    Ùħائة
    0.09
    ï¸ı
    0.09
    Ì
    0.09
    andainya
    0.08
    à¹Ģหลีà¹Īยม
    0.08
    szor
    0.08
    ãģ¤ãģ®
    0.08
    Activations Density 0.907%

    No Known Activations