© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20716
    Prev
    Next
    INDEX
    Explanations

    Ricci's

    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
     scand
    -0.07
    Ñģловно
    -0.07
    anteed
    -0.07
    èĩªæĭĶ
    -0.07
    /is
    -0.07
    .Must
    -0.07
    åĽłåľ°åĪ¶å®ľ
    -0.07
    ¿IJ
    -0.06
     Sor
    -0.06
     sor
    -0.06
    POSITIVE LOGITS
    leta
    0.07
    ortes
    0.07
    æ±ĩæĢ»è¡¨
    0.07
    Squared
    0.07
    ãģĭãĤı
    0.07
    åįĹå®ī
    0.07
    rots
    0.06
    ĵĺ
    0.06
    åij¨åħ¬
    0.06
    硬é«Ķ
    0.06
    Activations Density 0.004%

    No Known Activations