© 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. 63627
    Prev
    Next
    INDEX
    Explanations

    spices or wine names

    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
    <|box_end|>
    -0.08
    ities
    -0.07
    iveness
    -0.07
    sito
    -0.07
    iable
    -0.07
    toor
    -0.07
    urez
    -0.07
    æľªçĦ¶
    -0.07
    erior
    -0.07
    uters
    -0.07
    POSITIVE LOGITS
    λαν
    0.07
    seau
    0.07
    aldo
    0.07
     Ãģr
    0.07
    尼迪
    0.07
    çļİ
    0.06
    ianos
    0.06
    ç¾Į
    0.06
    νÏĮ
    0.06
    vens
    0.06
    Activations Density 0.001%

    No Known Activations