© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    `b` followed by `=`

    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
    ableView
    -0.08
    åĶ¯ä¸Ģä¸Ģ个
    -0.08
    VOKE
    -0.07
     Tauf
    -0.07
    ç½ij讯
    -0.07
    /extensions
    -0.07
    å¸Ĥæĸ°
    -0.07
    uncture
    -0.07
    çħ¦
    -0.07
    :\/\/
    -0.07
    POSITIVE LOGITS
    ¥
    0.07
    èij¬
    0.07
    éĥ¨
    0.07
    s
    0.07
    缸
    0.07
    åºĵå°Ķ
    0.07
    å¹½
    0.06
    çŁ¥
    0.06
    çļĦ大èĦij
    0.06
    åĸĭ
    0.06
    Activations Density 0.032%

    No Known Activations