© 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. 26435
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    çĤ¹å¯¹
    -0.07
    alai
    -0.07
    liku
    -0.06
    åĢ¼å¾Ĺ
    -0.06
    mlink
    -0.06
    UnderTest
    -0.06
    é¨ĵ
    -0.06
    踵
    -0.06
    款
    -0.06
    ãĤ¼ãĥ«
    -0.06
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.10
     ë¹Ħ롯íķľ
    0.08
    æĸ¹éĿ¢æľī
    0.08
    çŃīéĩįè¦ģ
    0.07
    normalize
    0.07
    çŃīåħ¶ä»ĸ
    0.07
     Äijai
    0.07
    æĸ¹éĿ¢
    0.07
    chia
    0.07
    çŃīåIJĦæĸ¹éĿ¢
    0.07
    Activations Density 0.472%

    No Known Activations