© 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. 58608
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators or punctuation

    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
    ihn
    -0.07
    rer
    -0.07
    riz
    -0.07
    utin
    -0.07
    ÃŃr
    -0.07
    ainted
    -0.07
    ç»Ī
    -0.06
    à¹Ģà¸Ĭ
    -0.06
    综
    -0.06
    lik
    -0.06
    POSITIVE LOGITS
    æ°¸åĴĮ
    0.08
    å¸
    0.08
    ัส
    0.07
    hare
    0.07
    eldo
    0.07
    allery
    0.07
    ervo
    0.07
    atico
    0.07
    ãģĭãĤĬ
    0.06
    atron
    0.06
    Activations Density 0.090%

    No Known Activations