© 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. 11677
    Prev
    Next
    INDEX
    Explanations

    intensifiers preceding adjectives

    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
    æĺıæĺı
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.07
     duly
    -0.07
    actly
    -0.07
    less
    -0.07
    ĻĤ
    -0.07
    足足
    -0.07
     Hälfte
    -0.07
    èĻ½å°ı
    -0.07
     sufficiently
    -0.07
    POSITIVE LOGITS
    /ext
    0.08
     (>
    0.08
    æŀģ端
    0.07
    æīįæľīåı¯èĥ½
    0.07
    æ¯Ķå¦Ĥ
    0.07
    çľģåİ»
    0.07
     Talvez
    0.06
     ultra
    0.06
    ä¸įçĶ¨
    0.06
    æĪĸ许
    0.06
    Activations Density 0.108%

    No Known Activations