© 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. 9411
    Prev
    Next
    INDEX
    Explanations

    use of

    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
    åģļæ³ķ
    -0.12
    æľīä¸Ģ天
    -0.11
    èµĸ以
    -0.11
    åħ³éĶ®æŶåĪ»
    -0.11
    认è¯Ĩ
    -0.10
    çļĦåģļæ³ķ
    -0.10
    çİ©æ³ķ
    -0.09
    alf
    -0.09
    ier
    -0.09
    æĢİä¹Īåģļ
    -0.09
    POSITIVE LOGITS
    åħĪè¿ĽæĬĢæľ¯
    0.11
    è¿Ļç§įæĸ¹å¼ı
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.10
     caution
    0.10
    åĴĮåıijå±ķ
    0.10
    eness
    0.10
    å®Įæ¯ķ
    0.09
    欺éªĹ
    0.09
    å®ĥåı¯ä»¥
    0.09
    åħĪè¿Ľ
    0.08
    Activations Density 0.075%

    No Known Activations