© 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. 11322
    Prev
    Next
    INDEX
    Explanations

    leading to/resulting in"""

    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
    ãĢģ“
    -0.08
    åīį款
    -0.08
     preoc
    -0.08
    å·¥ä½ľçļĦåIJĮæŶ
    -0.08
    好åķ¦
    -0.08
    并éĿŀæĺ¯
    -0.07
    à¤Ĺा
    -0.07
    вне
    -0.07
    olicitud
    -0.07
    меÑģÑĤи
    -0.07
    POSITIVE LOGITS
     appunto
    0.09
     سÙĬÙħا
    0.08
    beit
    0.08
     namely
    0.08
    åį³
    0.08
    åIJİèĢħ
    0.08
    ï½ŀãĢĤ
    0.08
     respectively
    0.07
    亦çĦ¶
    0.07
     że
    0.07
    Activations Density 0.863%

    No Known Activations