© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61885
    Prev
    Next
    INDEX
    Explanations

    charts and graphs

    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
     Kino
    -0.08
    å±ĢéĿ¢
    -0.07
    akash
    -0.07
    ansk
    -0.07
    åĽĽå¤Ħ
    -0.07
    æĥħç»ĵ
    -0.07
    çİ©ç¬ij
    -0.07
    .seed
    -0.07
    allen
    -0.07
    å±±ä¸Ń
    -0.07
    POSITIVE LOGITS
    åĽ¾è¡¨
    0.10
    æķ°æį®çļĦ
    0.10
    æķ°æį®
    0.10
    ãĤ°ãĥ©ãĥķ
    0.09
     data
    0.09
     graph
    0.09
     graphs
    0.09
    æķ°æį®è¿Ľè¡Į
    0.08
    çļĦæķ°æį®
    0.08
    data
    0.08
    Activations Density 0.098%

    No Known Activations