© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    if this

    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
    ayne
    -0.08
    инÑģÑĤва
    -0.08
    ackle
    -0.08
    zyma
    -0.08
    riba
    -0.08
    åĩ¡
    -0.07
     essenz
    -0.07
    nown
    -0.07
    adge
    -0.07
    akeup
    -0.07
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    ä¸įæħİ
    0.09
    åĪĻä¼ļ
    0.09
    以任ä½ķ
    0.08
    羣çļĦæľī
    0.07
    å·¥ä½ľéľĢè¦ģ
    0.07
    ä¸įå°ıå¿ĥ
    0.07
     ÙģØ¥ÙĨ
    0.07
    æŀľçľŁ
    0.07
     окажеÑĤÑģÑı
    0.07
    Activations Density 0.355%

    No Known Activations