© 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. 9201
    Prev
    Next
    INDEX
    Explanations

    dynasty, monarchy, overthrown, rise

    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
    è°
    -0.10
    .enc
    -0.10
    ä¸ĩçī©
    -0.09
    rovers
    -0.09
    åıĮèĦļ
    -0.08
    æ²³åĮĹ
    -0.08
    æºŁ
    -0.08
    ERICA
    -0.08
    elman
    -0.08
    追踪
    -0.08
    POSITIVE LOGITS
    æĶ¿æĿĥ
    0.19
    åŀ®
    0.15
    ç»Łæ²»
    0.11
    æī§æĶ¿
    0.11
    å´©æºĥ
    0.11
     вла
    0.11
     overthrow
    0.11
    çģŃ亡
    0.10
    é¢łè¦Ĩ
    0.10
    建ç«ĭäºĨ
    0.10
    Activations Density 0.072%

    No Known Activations