© 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. 20827
    Prev
    Next
    INDEX
    Explanations

    conjunctions and 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
    antas
    -0.07
    åĪĽ
    -0.07
    اÙĨÙĪÙĨ
    -0.06
    ász
    -0.06
    antz
    -0.06
    ivas
    -0.06
    æ¦Ĥ论
    -0.06
    antina
    -0.06
     pretext
    -0.06
    èĩ³æѤ
    -0.06
    POSITIVE LOGITS
    aglio
    0.09
    åĵªäºĽ
    0.08
    _ALIGNMENT
    0.08
    ftar
    0.07
    ugada
    0.07
    åĵªäºĽæĸ¹éĿ¢
    0.07
    ’T
    0.07
    è¿Ļä¹Ī大çļĦ
    0.07
    hart
    0.07
    ever
    0.07
    Activations Density 0.001%

    No Known Activations