© 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. 62008
    Prev
    Next
    INDEX
    Explanations

    +/- SD

    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
    Ñĩе
    -0.06
    è¦ģåģļ好
    -0.06
    ossi
    -0.06
    §
    -0.06
    care
    -0.06
     nag
    -0.06
    çģ
    -0.06
    1
    -0.06
    —
    -0.05
    ogn
    -0.05
    POSITIVE LOGITS
    ä¾Ŀ次为
    0.10
    åĪĨåĪ¥æĺ¯
    0.09
    )=(
    0.09
    ocoder
    0.09
    åĪĨåĪ«ä¸º
    0.09
     desto
    0.09
    liwoÅĽÄĩ
    0.08
    ayout
    0.08
     ialah
    0.08
    InOut
    0.08
    Activations Density 0.016%

    No Known Activations