© 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. 37218
    Prev
    Next
    INDEX
    Explanations

    giant companies and makers

    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
    çľĭä¸Ĭåİ»
    -0.10
    åī¡
    -0.10
    isters
    -0.09
    PIO
    -0.09
    æĺ¯æ¯Ķè¾ĥ
    -0.09
    ç²¾åįİ
    -0.09
    æĺµ
    -0.09
    rpc
    -0.09
    æīįç®Ĺ
    -0.09
    å±ħ室
    -0.09
    POSITIVE LOGITS
    igh
    0.09
    æħ£
    0.08
    åĩºçīĪ社
    0.08
    é³Į
    0.08
    巨头
    0.08
    积æŀģ
    0.08
    éħ½
    0.08
    ESC
    0.08
     Cruise
    0.08
    -grand
    0.08
    Activations Density 0.034%

    No Known Activations