© 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. 41211
    Prev
    Next
    INDEX
    Explanations

    collect terms in

    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
     sekian
    -0.08
    ishi
    -0.08
    Ïħνα
    -0.07
    å¤Ħå¤Ħ
    -0.07
    æķĻèĤ²åİħ
    -0.07
    doc
    -0.07
    çĶ»å»Ĭ
    -0.07
    ray
    -0.07
    лÑİÑĩ
    -0.07
    ÑĢиÑģÑĤа
    -0.06
    POSITIVE LOGITS
     terms
    0.08
    æĪijä¸Ģ个人
    0.08
    ä¸ŃåĮº
    0.08
    ä¹ĭå·®
    0.07
    legs
    0.07
    اصÙĦ
    0.07
     Legs
    0.07
    Sans
    0.07
    ":["
    0.07
    äºİä¸Ģ身
    0.07
    Activations Density 0.003%

    No Known Activations