© 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. 48986
    Prev
    Next
    INDEX
    Explanations

    layer

    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
    åij½åIJį
    -0.06
     kalk
    -0.06
    åħĪåľ¨
    -0.06
    erva
    -0.06
    ervi
    -0.06
    æį§
    -0.06
    çĤ¹å·¦åı³
    -0.06
     (
    -0.06
    .getComponent
    -0.06
    zek
    -0.06
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.10
    ìĿ´ëŀĢ
    0.10
    æĮĩçļĦ
    0.10
    æĺ¯æĮĩåľ¨
    0.10
     refers
    0.10
    æĮĩ
    0.09
    æĺ¯æĮĩ
    0.09
     หมายà¸ĸึà¸ĩ
    0.08
    æĶ¶ä»¶
    0.08
    [âĢ¦]
    0.08
    Activations Density 0.027%

    No Known Activations