© 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. 17684
    Prev
    Next
    INDEX
    Explanations

    diagrams and figures

    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
    ä¸İèĩªçĦ¶
    -0.07
     no
    -0.06
    /
    -0.06
     everywhere
    -0.06
     minor
    -0.06
    èĥ½ä¸İ
    -0.06
    被åĪ«äºº
    -0.06
    :
    -0.06
     imm
    -0.06
    ä¸İå°ı
    -0.06
    POSITIVE LOGITS
     illustrates
    0.10
    Insets
    0.09
     outlines
    0.09
    onha
    0.08
    ÑĥÑģÑĤа
    0.08
    illustr
    0.08
    对æѤ
    0.08
    bruck
    0.08
    æīĢ示
    0.08
    å°±æѤ
    0.08
    Activations Density 0.067%

    No Known Activations