© 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. 14493
    Prev
    Next
    INDEX
    Explanations

    . followed by words

    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
    ugier
    -0.07
    ÑĢÑİ
    -0.07
    ĩ
    -0.07
    inaan
    -0.07
    ạch
    -0.06
    ç´«èĸĩ
    -0.06
    roperty
    -0.06
    ä¸įèĥľ
    -0.06
    Narrated
    -0.06
    öd
    -0.06
    POSITIVE LOGITS
    è¹ĭ
    0.07
     tá
    0.07
    å®Ĺ主
    0.07
    æij¸çĿĢ
    0.07
    åĪ°çİ°åľº
    0.07
     callBack
    0.06
     Fras
    0.06
    .Clone
    0.06
    äºijå±±
    0.06
    _touch
    0.06
    Activations Density 0.036%

    No Known Activations