© 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. 29896
    Prev
    Next
    INDEX
    Explanations

    kind of phrase

    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
    fone
    -0.08
    abelle
    -0.08
    ئÙĩ
    -0.08
    åı¥åı¥
    -0.07
    otá
    -0.07
     impeccable
    -0.07
     reportedly
    -0.07
    skraft
    -0.07
     vã
    -0.07
    subpackage
    -0.07
    POSITIVE LOGITS
    å°±åĥıæĺ¯
    0.11
    ä¸Ģç§į
    0.09
    就好åĥı
    0.09
    åĥıæĺ¯
    0.09
     ÑģвоеобÑĢаз
    0.09
    æŁIJç§į
    0.08
    alog
    0.08
    æıIJä¾Ľä¸Ģç§į
    0.08
    好æ¯Ķ
    0.08
     akin
    0.08
    Activations Density 0.120%

    No Known Activations