© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    quantum computing and cryptography

    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
    akk
    -0.09
    avia
    -0.09
    éĢĢåĽŀ
    -0.08
    оÑĩ
    -0.08
    ÇIJ
    -0.08
    .getAmount
    -0.08
     Welch
    -0.08
    _CHARSET
    -0.08
    ä¸Ģåı£
    -0.08
    éĥ¨éŨ
    -0.08
    POSITIVE LOGITS
    amin
    0.10
    æĢĿç»´
    0.10
    ium
    0.10
    身æĹģ
    0.09
    å¤ĸçķĮ
    0.09
     Emanuel
    0.09
    6
    0.09
    å°ķ
    0.09
    7
    0.09
     Tube
    0.08
    Activations Density 0.336%

    No Known Activations