© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1371
    Prev
    Next
    INDEX
    Explanations

    "-only" followed by a noun

    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
     enough
    -0.25
    	auth
    -0.23
    arest
    -0.22
     utmost
    -0.22
    éļĽ
    -0.21
    ادر
    -0.20
    åŃº
    -0.20
    bam
    -0.20
    鼩
    -0.20
    (comm
    -0.20
    POSITIVE LOGITS
    æĪĸèĢħ
    0.25
    /Private
    0.23
    nika
    0.23
    xing
    0.23
    模å¼ı
    0.22
     creations
    0.22
    Supply
    0.22
    ç§ģä¸ĭ
    0.21
    /off
    0.21
     proceedings
    0.20
    Activations Density 0.013%

    No Known Activations