© 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. 981
    Prev
    Next
    INDEX
    Explanations

    mythological names and terms

    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
    æķĻ主
    -0.07
     organ
    -0.06
    æķĻå¾Ĵ
    -0.06
    åħī绪
    -0.06
     Chauff
    -0.06
     оÑĢганаÑħ
    -0.06
    马路
    -0.06
     Howell
    -0.06
     saf
    -0.06
     Street
    -0.06
    POSITIVE LOGITS
    impa
    0.09
    ezen
    0.09
    æİĴè¡Į
    0.08
     bers
    0.08
    ichel
    0.08
     epic
    0.08
    åĩ¡
    0.08
    æĸŁ
    0.08
    coes
    0.08
     Bronze
    0.08
    Activations Density 0.043%

    No Known Activations