© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2118
    Prev
    Next
    INDEX
    Explanations

    with your/our/the/a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢèĪ¬äºº
    -0.25
    æ±Łæ¹ĸ
    -0.24
     Presidency
    -0.23
     Himself
    -0.23
    raq
    -0.22
    /OR
    -0.21
    imat
    -0.21
     outsiders
    -0.21
    anded
    -0.21
    /assert
    -0.21
    POSITIVE LOGITS
     specially
    0.29
     Visual
    0.28
     dedicated
    0.26
     customizable
    0.25
     guided
    0.25
     themed
    0.25
     Orig
    0.25
     specialized
    0.25
     variety
    0.25
     versatile
    0.24
    Activations Density 0.050%

    No Known Activations