© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    intensifiers followed by adjectives

    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
     Entire
    -0.30
    æĽ´å¤§çļĦ
    -0.29
    æĽ´é«ĺ
    -0.28
    æĽ´æ·±
    -0.28
    æĽ´å¤ļçļĦ
    -0.28
    æĽ´å¤ļ
    -0.26
    æĽ´é«ĺçļĦ
    -0.26
    ç»ĪçĶŁ
    -0.26
    ç»Ī身
    -0.24
    ä¸Ģå®ļç¨ĭ度
    -0.23
    POSITIVE LOGITS
     sensitive
    0.24
    é«ĺçļĦ
    0.24
     (>
    0.23
     fluid
    0.23
     debated
    0.22
    çģµæķı
    0.22
     visible
    0.22
    æľīåIJįçļĦ
    0.21
    大çļĦ
    0.21
     ac
    0.21
    Activations Density 0.081%

    No Known Activations