© 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. 49207
    Prev
    Next
    INDEX
    Explanations

    numbers and durations

    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
    et
    -0.07
    ret
    -0.06
    寸
    -0.06
    angu
    -0.06
    å°ģ
    -0.06
    ares
    -0.06
    _TRANSACTION
    -0.06
    æī¿åıĹ
    -0.06
    aes
    -0.06
    ä»»
    -0.06
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.10
    ä¹ĥèĩ³
    0.10
    çĶļèĩ³æĺ¯
    0.09
    åĴĮäºĮ
    0.09
     voire
    0.08
    IEWS
    0.08
    RICS
    0.08
    å¹¶ä½ľ
    0.08
    çİ¥
    0.08
     ÙĪاÙĦØ«
    0.08
    Activations Density 0.316%

    No Known Activations