© 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. 9268
    Prev
    Next
    INDEX
    Explanations

    after followed by an event

    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
    éģ½
    -0.11
    åľĪ
    -0.09
    éĥ½è¯´
    -0.08
    çĽĹ
    -0.08
    æĺĨä»ij
    -0.08
     geçen
    -0.08
    ä¹Łä¸º
    -0.08
    åľĪåŃIJ
    -0.08
    è¿Ļ个æŶåĢĻ
    -0.08
    骤
    -0.08
    POSITIVE LOGITS
    åĬªåĬĽ
    0.12
    éģµå¾ª
    0.10
    ç»ıè¿ĩ
    0.10
    æ·±å±Ĥ
    0.09
    æĪIJçĨŁçļĦ
    0.09
    åĨĴçĿĢ
    0.09
     taps
    0.09
    -inner
    0.08
    jour
    0.08
    ä»ĺåĩº
    0.08
    Activations Density 0.074%

    No Known Activations