© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23498
    Prev
    Next
    INDEX
    Explanations

    absolute

    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
    lighet
    -0.10
    psilon
    -0.09
    manship
    -0.09
    nable
    -0.09
    ç»´åIJ¾å°Ķèĩªæ²»åĮº
    -0.09
    hap
    -0.09
    kad
    -0.09
    ighed
    -0.08
    regor
    -0.08
    erei
    -0.08
    POSITIVE LOGITS
    OLUTE
    0.09
    ity
    0.08
    itude
    0.07
    -ish
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    ensee
    0.06
    ض
    0.06
    -minded
    0.06
    æºľæºľ
    0.06
    ive
    0.06
    Activations Density 0.008%

    No Known Activations