© 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. 55897
    Prev
    Next
    INDEX
    Explanations

    invariant or unchanged state

    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
    寿åİ¿
    -0.07
    à¹Ģà¸ķà¹ĩมà¸Ĺีà¹Ī
    -0.07
    eho
    -0.07
    tridge
    -0.07
    quee
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
     knowingly
    -0.07
    åĪĩ身
    -0.06
    æľīéĴĪ对æĢ§çļĦ
    -0.06
    (dirname
    -0.06
    POSITIVE LOGITS
    ä¿ĿæĮģä¸įåıĺ
    0.15
    ä¸įåıĺçļĦ
    0.15
    ä¸įåıĺ
    0.14
     invariant
    0.13
     preserved
    0.13
    Invariant
    0.13
    å®ĪæģĴ
    0.12
    æģĴå®ļ
    0.12
     unchanged
    0.11
     ÑģоÑħÑĢанÑıеÑĤÑģÑı
    0.11
    Activations Density 0.009%

    No Known Activations