© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31385
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åľ¨è·¯ä¸Ĭ
    -0.10
    hamster
    -0.09
    å¼ŁåŃIJ
    -0.09
    Glass
    -0.08
    转载请
    -0.08
    åŃIJåŃĻ
    -0.08
    Clients
    -0.08
     glass
    -0.08
    åѦçĶŁä»¬
    -0.08
    ħĮ
    -0.08
    POSITIVE LOGITS
    æľīä¸Ģä½į
    0.21
    æĺ¯çĶ±
    0.20
    çĶ±
    0.18
    åĿĩçĶ±
    0.17
    æĺ¯è°ģ
    0.16
    两ä½į
    0.16
    ä¸īä½į
    0.15
    ä¸ĵ人
    0.15
    åĩºèĩª
    0.15
    çĶ±ä¸ŃåĽ½
    0.14
    Activations Density 0.319%

    No Known Activations