© 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. 64327
    Prev
    Next
    INDEX
    Explanations

    given a

    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
    cik
    -0.07
    æħij
    -0.07
    æĤ
    -0.06
    γο
    -0.06
     contend
    -0.06
    ļľ
    -0.06
    nbsp
    -0.06
    Ñģлов
    -0.06
    à¸Ńà¸Ĺ
    -0.06
    går
    -0.06
    POSITIVE LOGITS
     given
    0.10
    ç»Ļå®ļ
    0.10
    åĽºå®ļçļĦ
    0.09
    ajer
    0.08
    given
    0.08
    ä¸Ĭè¿°
    0.08
    ç»Ļ
    0.07
     gegeben
    0.07
     _______,
    0.07
    kes
    0.07
    Activations Density 0.019%

    No Known Activations