© 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. 41179
    Prev
    Next
    INDEX
    Explanations

    orbit chart groups

    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
    èĥ¸èĨĽ
    -0.07
    am
    -0.07
    临
    -0.06
    Ñģловно
    -0.06
    æĵį
    -0.06
     bách
    -0.06
    æĿ¾äºĨä¸Ģåı£æ°Ķ
    -0.06
    em
    -0.06
     겸
    -0.06
    overall
    -0.06
    POSITIVE LOGITS
     orbit
    0.09
    è©®
    0.09
    ç»ĦåĴĮ
    0.09
    ĶĦ
    0.09
    ç»Ħåijĺ
    0.08
    ç»ĦæĪIJåijĺ
    0.08
    循çݯ
    0.08
    çµĦ
    0.08
    循çĴ°
    0.08
    ruf
    0.08
    Activations Density 0.005%

    No Known Activations