© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 19
    Prev
    Next
    INDEX
    Explanations

    active duty

    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
    å¼Ģåı£
    -0.21
    ROUND
    -0.21
    //[
    -0.21
    å¼Ī
    -0.21
    ä¸įäºĨ
    -0.20
    ä¸ºçĽ®æłĩ
    -0.20
    ¦Ĥ
    -0.20
    AMES
    -0.20
    è°¯
    -0.20
    æľīè¿ĩ
    -0.20
    POSITIVE LOGITS
     mode
    0.31
    çĬ¶æĢģ
    0.30
     guise
    0.28
    çĭĢæħĭ
    0.27
    -mode
    0.27
     accordance
    0.26
    åľ°ä½į
    0.26
    çĬ¶æĢģä¸ĭ
    0.26
    ä¹ĭä¸Ń
    0.24
     behalf
    0.23
    Activations Density 0.152%

    No Known Activations