© 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. 63646
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    æ±¹
    -0.08
    å¯Ħ宿
    -0.08
    alon
    -0.08
    大éĥ¨
    -0.07
     Sext
    -0.07
    é¡į
    -0.07
    èĩªä½ľ
    -0.06
    åĬĽå£«
    -0.06
     Zwie
    -0.06
    agy
    -0.06
    POSITIVE LOGITS
    尾巴
    0.07
    CHK
    0.07
    èݺ
    0.07
    gire
    0.06
    åįĹäºļ
    0.06
    åŀ¢
    0.06
    å°¾
    0.06
     tail
    0.06
    dden
    0.06
    就差
    0.06
    Activations Density 0.010%

    No Known Activations