© 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. 49036
    Prev
    Next
    INDEX
    Explanations

    engagement or metadata text

    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
    iped
    -0.08
    è¦ģæ±Ĥèĩªå·±
    -0.07
    鸳
    -0.07
    ÑģлÑĮ
    -0.07
     ↵ ↵
    -0.07
    rash
    -0.07
    ç»Ĭ
    -0.07
    çļĦçļ®èĤ¤
    -0.06
    çļĦ为
    -0.06
    æĢ¥äºİ
    -0.06
    POSITIVE LOGITS
    `t
    0.08
    ######
    0.08
    inho
    0.07
    >L
    0.07
    .Cryptography
    0.07
    .compute
    0.07
    clone
    0.06
    大浪
    0.06
    cond
    0.06
    ct
    0.06
    Activations Density 0.196%

    No Known Activations