© 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. 27363
    Prev
    Next
    INDEX
    Explanations

    after temp

    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
    æľīçĹħ
    -0.07
    ä¾
    -0.07
    èĵ
    -0.06
     sat
    -0.06
    çĹħ
    -0.06
    æĺİ
    -0.06
     am
    -0.06
    èĩªçĦ¶èµĦæºIJåĴĮ
    -0.06
    éł
    -0.06
    究竣æĺ¯
    -0.05
    POSITIVE LOGITS
    -holder
    0.09
    yip
    0.09
    UGHT
    0.08
    ween
    0.08
    uela
    0.08
    ãģıãĤĵ
    0.08
    ụt
    0.07
    æ¯İ
    0.07
     adres
    0.07
    opf
    0.07
    Activations Density 0.075%

    No Known Activations