© 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. 22361
    Prev
    Next
    INDEX
    Explanations

    essential or crucial

    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
    ä½ķå¿ħ
    -0.09
     Yourself
    -0.08
    ufr
    -0.08
    reek
    -0.08
    并使çĶ¨
    -0.08
    å¹¶è¿Ľè¡Į
    -0.08
    RelativeTo
    -0.07
    ervis
    -0.07
    åıĬéĶĢåĶ®
    -0.07
     taas
    -0.07
    POSITIVE LOGITS
     Äijá»ĥ
    0.08
    ç»´æĮģ
    0.08
    æŀģäºĨ
    0.08
    çIJĨ解
    0.08
    ç¡®ä¿Ŀ
    0.07
     understanding
    0.07
     riuscita
    0.07
    èĥ½åIJ¦
    0.07
     maintaining
    0.07
     banget
    0.07
    Activations Density 0.107%

    No Known Activations