© 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. 20495
    Prev
    Next
    INDEX
    Explanations

    epithet or something that describes

    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
    æ½ľåĬĽ
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    _PROTO
    -0.08
    annel
    -0.08
    ẻo
    -0.08
     potentials
    -0.08
    edy
    -0.07
    кипа
    -0.07
    опо
    -0.07
    rena
    -0.07
    POSITIVE LOGITS
    并åĪĹ
    0.09
     something
    0.08
     synonymous
    0.07
    修饰
    0.07
     name
    0.07
    形容è¯į
    0.07
     Something
    0.07
    请填åĨĻ
    0.07
     noun
    0.07
    å®ļè¯Ń
    0.07
    Activations Density 0.004%

    No Known Activations