© 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. 31692
    Prev
    Next
    INDEX
    Explanations

    temporal or duration phrases

    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
    опаÑģ
    -0.08
    çķĻæģĭ
    -0.08
    иÑģк
    -0.07
    æľ¬äººåľ¨
    -0.07
    ÑĨеп
    -0.07
    onais
    -0.07
    ä¸Ģåıį
    -0.07
    æĪĸå°Ĩ
    -0.07
     Noel
    -0.07
    .constructor
    -0.07
    POSITIVE LOGITS
    èĢĮä¸Ķ
    0.08
    à¹ģละà¹Ħมà¹Ī
    0.08
    T
    0.08
    ä¸Ķ
    0.08
    以åıĬå¦Ĥä½ķ
    0.08
     à¹ģละà¹Ħมà¹Ī
    0.07
    ä¸Ķä¸į
    0.07
    t
    0.07
    and
    0.07
    以åıĬ对
    0.07
    Activations Density 0.007%

    No Known Activations