© 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. 28986
    Prev
    Next
    INDEX
    Explanations

    code or other fields

    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
    sak
    -0.09
    à¹ģละสà¹Īà¸ĩ
    -0.08
    åįķä¸ĢçļĦ
    -0.08
    ãĥ¬ãĥĥãĥĪ
    -0.08
    ↵    ↵    ↵
    -0.08
    oya
    -0.08
    ↵↵    ↵
    -0.08
    essler
    -0.08
    ById
    -0.07
    ByName
    -0.07
    POSITIVE LOGITS
    æĢ
    0.06
    èĬ
    0.06
     refin
    0.06
    ^^
    0.06
    upe
    0.06
    æķı
    0.06
     Nobel
    0.05
    osten
    0.05
    ente
    0.05
     depending
    0.05
    Activations Density 0.015%

    No Known Activations