© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    questions or statements

    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©
    -0.05
    ä¹ħèĢĮ
    -0.05
    (
    -0.05
    9
    -0.05
    -
    -0.05
     interp
    -0.05
    >
    -0.05
     bound
    -0.05
    "
    -0.05
    å·Ŀ
    -0.05
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    ấu
    0.09
    ongan
    0.09
    ãĥ¼ãĥģ
    0.08
    odz
    0.08
    æĺ¯ä½ķåIJ«ä¹ī
    0.08
    ÑģмоÑĤÑĢÑı
    0.08
    ParameterValue
    0.08
    رÛĮاÙĨ
    0.08
    æĪijçļĦä¼ģä¸ļ
    0.08
    Activations Density 0.016%

    No Known Activations