© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22203
    Prev
    Next
    INDEX
    Explanations

    chatting online or using IRC bots

    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
    çīĩåŃIJ
    -0.11
    éķĤ
    -0.10
    èŀ³
    -0.10
    æ¯ıå¹´éĥ½
    -0.09
    æŃ»äºĨ
    -0.09
    .Marshal
    -0.09
    _Back
    -0.09
    lemn
    -0.09
     Conj
    -0.08
    ä»İæĿ¥ä¸į
    -0.08
    POSITIVE LOGITS
     chat
    0.14
    èģĬ天
    0.14
    Chat
    0.11
    -chat
    0.11
     Chat
    0.11
     online
    0.11
     chats
    0.10
    æĪ¿éĹ´
    0.10
    /chat
    0.10
    chat
    0.10
    Activations Density 0.148%

    No Known Activations