© 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. 41297
    Prev
    Next
    INDEX
    Explanations

    denote or deliver values

    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
    ...).
    -0.09
    ï¸ı
    -0.08
    è¿ĻäºĭåĦ¿
    -0.08
    FromBody
    -0.08
    âĢ¼
    -0.07
    æ§ĥ
    -0.07
    让è¿ĻäºĽ
    -0.07
    ...</
    -0.07
    née
    -0.07
    á´Ľ
    -0.07
    POSITIVE LOGITS
     evidently
    0.08
    æĪĸæĺ¯
    0.07
    å¦Ĥä¸ĭ
    0.07
     Ebay
    0.07
     duly
    0.07
    .case
    0.07
    seo
    0.07
    çĽ¸å¯¹åºĶçļĦ
    0.06
     firstly
    0.06
     altogether
    0.06
    Activations Density 0.022%

    No Known Activations