© 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. 33303
    Prev
    Next
    INDEX
    Explanations

    following a methodology

    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
    ngle
    -0.08
    ाय
    -0.07
    egl
    -0.07
    mys
    -0.07
    chl
    -0.07
    å¤§åľ°éľĩ
    -0.07
    rul
    -0.07
    pä
    -0.07
    ä¸īæĶ¯ä¸Ģæī¶
    -0.07
    à¥įरा
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæŃ¥éª¤
    0.09
     outlined
    0.09
     steps
    0.09
    æŃ¥é©Ł
    0.09
     postup
    0.08
     above
    0.08
    æŃ¥éª¤
    0.08
    à¸Ĥัà¹īà¸Ļà¸ķà¸Ńà¸Ļ
    0.08
     Steps
    0.07
    ä¸ĬéĿ¢
    0.07
    Activations Density 0.085%

    No Known Activations