© 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. 42604
    Prev
    Next
    INDEX
    Explanations

    Grade II listed buildings, reproductive ratio, index

    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
    Uses
    -0.08
    çĶ±äºİåħ¶
    -0.07
    pite
    -0.07
    åĽłä¸ºåħ¶
    -0.07
    auga
    -0.07
    æĹłæŀģ
    -0.07
    ç¾ŀ
    -0.07
    ido
    -0.07
    agno
    -0.06
    åĽłä¸ºè¿Ļ个
    -0.06
    POSITIVE LOGITS
    æĺ¯æĮĩ
    0.12
    æĺ¯æĮĩåľ¨
    0.11
    æĦı为
    0.10
    æĦıæĢĿæĺ¯
    0.10
    ä¸Ń表示
    0.10
    æĮĩ
    0.10
     meaning
    0.10
    çļĦæĦıæĢĿæĺ¯
    0.09
    表示
    0.09
    çļĦåIJ«ä¹ī
    0.09
    Activations Density 0.138%

    No Known Activations