© 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. 1595
    Prev
    Next
    INDEX
    Explanations

    transition, change, condition, variability, bindings

    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
    éħ®
    -0.23
    åijĭ
    -0.23
     Antar
    -0.23
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.23
    çļ²
    -0.22
    亥
    -0.22
    ä¸Ĭæµ·è¯ģåĪ¸
    -0.22
     Breed
    -0.22
    åľ¨çİ°åľº
    -0.22
     Suppress
    -0.22
    POSITIVE LOGITS
    çļĦçݰ象
    0.27
     movement
    0.25
    çļĦçĬ¶æĢģ
    0.24
    çļĦæĥħåĨµ
    0.24
    /per
    0.24
    å¼ıçļĦ
    0.24
    为主çļĦ
    0.24
    å¶
    0.24
     dynamics
    0.24
    çļĦå¿ĥæĢģ
    0.23
    Activations Density 0.238%

    No Known Activations