© 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. 61572
    Prev
    Next
    INDEX
    Explanations

    definition or quote source

    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
    çīĩçīĩ
    -0.08
    ä¹ĭæĹħ
    -0.08
    .fil
    -0.08
    åIJĦ个çݯèĬĤ
    -0.08
    erc
    -0.07
    åIJijåħ¶
    -0.07
    өг
    -0.07
    åĬłåĭĴ
    -0.07
    èĿ
    -0.07
    	prop
    -0.07
    POSITIVE LOGITS
    å¥łå®ļäºĨ
    0.08
    èĤ¯å®ļäºĨ
    0.08
    ç¡®ç«ĭäºĨ
    0.07
    解éĩĬäºĨ
    0.07
    æĮĩåĩºäºĨ
    0.07
    inds
    0.07
    æĺİç¡®äºĨ
    0.07
    çĻ¾å¿Ļ
    0.07
    è§Ħå®ļäºĨ
    0.07
    ynd
    0.07
    Activations Density 0.045%

    No Known Activations