© 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. 23451
    Prev
    Next
    INDEX
    Explanations

    differential amplification, dilution, signal

    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¸į缺
    -0.08
    毫ä¸į
    -0.08
    æ¯ı家
    -0.08
    ÄĻż
    -0.08
    erso
    -0.07
    dsn
    -0.07
    æ¡Ī
    -0.07
     bando
    -0.07
    auen
    -0.07
     меди
    -0.07
    POSITIVE LOGITS
     eliminates
    0.10
    æĬĹ
    0.10
    æ¶ĪéĻ¤
    0.09
    æĬµæ¶Ī
    0.09
     eliminating
    0.09
    åı¯ä»¥æľīæķĪ
    0.08
     eliminate
    0.08
     mitigate
    0.08
     canc
    0.08
     cancel
    0.08
    Activations Density 0.053%

    No Known Activations