© 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. 41427
    Prev
    Next
    INDEX
    Explanations

    treats, attention

    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
    ï¼ģï¼Ī
    -0.09
    !”
    -0.08
    ï¼ģ**
    -0.08
    !**
    -0.08
    ickl
    -0.08
    !")
    -0.07
    ï¼ģï¼ģï¼ģ
    -0.07
     –**
    -0.07
    .*)
    -0.07
    !*
    -0.07
    POSITIVE LOGITS
    ï¼Į
    0.08
    ,
    0.07
    ØĮ
    0.07
    áĥª
    0.07
    èĢĮå°±
    0.07
    èĭ¦è¾£
    0.06
    丰åİ¿
    0.06
    Vir
    0.06
    ori
    0.06
    attle
    0.06
    Activations Density 0.074%

    No Known Activations