© 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. 13494
    Prev
    Next
    INDEX
    Explanations

    ebook formats

    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
    ä¸ŀ缸
    -0.07
    mal
    -0.06
    Ä«bÄģ
    -0.06
    idders
    -0.06
    åģĩ
    -0.06
     [âĢ¦
    -0.06
    ÙĨدÙĩ
    -0.05
    amai
    -0.05
     sd
    -0.05
    ular
    -0.05
    POSITIVE LOGITS
    欢è¿İåħ³æ³¨
    0.07
    天é¾Ļ
    0.07
    ITAS
    0.07
    xEE
    0.07
    wana
    0.07
    ÑģÑĤик
    0.07
    íĥĿ
    0.07
    åīįèĮħ
    0.07
    山人
    0.07
    }$/
    0.07
    Activations Density 0.083%

    No Known Activations