© 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. 38599
    Prev
    Next
    INDEX
    Explanations

    around time

    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
    èĻı
    -0.12
    丰åİļ
    -0.10
    æ§Ľ
    -0.09
    RLF
    -0.09
    clair
    -0.09
    滥
    -0.09
    ä¾£
    -0.09
    SCRIPTOR
    -0.09
    ç¬ŀ
    -0.09
    å±ģèĤ¡
    -0.09
    POSITIVE LOGITS
    å½ĵæĻļ
    0.09
    两个å°ıæŶ
    0.09
    åĩĮæĻ¨
    0.08
    æĹ¶è®¸
    0.08
    æİ¥è¿ij
    0.08
    å¤ĸåĮħ
    0.08
    åıijçĶŁäºĨ
    0.08
    å¼ķåıijäºĨ
    0.08
    çĸij
    0.08
    è¿Ļ段
    0.07
    Activations Density 0.023%

    No Known Activations