© 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. 49500
    Prev
    Next
    INDEX
    Explanations

    channel current

    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
     à®ħà®°à®ļ
    -0.06
    顶å±Ĥ设计
    -0.06
     обаÑĩ
    -0.05
    å¾Ĺ天çĭ¬åİļçļĦ
    -0.05
    åįĥ家ä¸ĩæĪ·
    -0.05
     instansi
    -0.05
    æĮĩ示精ç¥ŀ
    -0.05
     Cumhuri
    -0.05
    .guild
    -0.05
    .MainActivity
    -0.05
    POSITIVE LOGITS
    åĬłæĭ¿å¤§çļĦ
    0.08
    èĬĿåĬł
    0.08
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    0.08
    WebKit
    0.08
    å½ĵåºŃ
    0.08
    (Android
    0.08
    çİĦå¹»éŃĶæ³ķ
    0.08
    utex
    0.08
    WebElement
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    Activations Density 15.398%

    No Known Activations