© 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. 29623
    Prev
    Next
    INDEX
    Explanations

    numbers, counts, or lists

    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
    æī§
    -0.08
    quent
    -0.08
    å¹´èıľ
    -0.08
    iros
    -0.08
    inand
    -0.07
    neze
    -0.07
     Alexis
    -0.07
    etag
    -0.07
    trop
    -0.07
    quet
    -0.07
    POSITIVE LOGITS
    æĬļ
    0.07
    é¹°
    0.07
    æĹĭ
    0.06
    åijĬ
    0.06
    ijker
    0.06
    èľ
    0.06
    ads
    0.06
     G
    0.06
    emis
    0.06
    çķ¥
    0.06
    Activations Density 0.585%

    No Known Activations