© 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. 19146
    Prev
    Next
    INDEX
    Explanations

    .js, .dart, txt, service, Entity, Upload

    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
    -0.07
    <|endoftext|>
    -0.06
     "
    -0.06
     Se
    -0.06
    online
    -0.06
    ç¦Ģ
    -0.06
    欲滴
    -0.05
    æ´ŀåºŃ
    -0.05
    1
    -0.05
     vs
    -0.05
    POSITIVE LOGITS
     izman
    0.08
    авли
    0.08
    .jd
    0.08
    ä¸Ģ鸣
    0.08
    æľīæĿĥä¿ĿçķĻ
    0.08
    ãĥ¼ãĥķ
    0.08
    )ãĢģ
    0.08
    ï¼īãĥ»
    0.08
     DOCUM
    0.08
    ÕŃ
    0.08
    Activations Density 0.035%

    No Known Activations