© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37359
    Prev
    Next
    INDEX
    Explanations

    former original usual

    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
    ä½°
    -0.11
    éķ¿å¯¿
    -0.11
    åģļçļĦäºĭæĥħ
    -0.10
    éľİ
    -0.10
    侯
    -0.10
    aversal
    -0.09
    çĶ¨äºº
    -0.09
    çļĦéŃħåĬĽ
    -0.09
    æŃĮ
    -0.09
     Mercer
    -0.09
    POSITIVE LOGITS
    è·¨
    0.09
    æ²Ĩ
    0.09
    ank
    0.09
    紧紧
    0.08
    åĪĿè¡·
    0.08
    bez
    0.08
     fert
    0.08
    iale
    0.08
    足以
    0.08
    ä¸ĩéĩĮ
    0.08
    Activations Density 0.047%

    No Known Activations