© 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. 52148
    Prev
    Next
    INDEX
    Explanations

    what happens

    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
    没æľīå¿ħè¦ģ
    -0.09
    ugg
    -0.09
     Seats
    -0.09
    éĩįè¦ģåĨħ容
    -0.09
    .Formatter
    -0.08
    éĩįè¦ģ
    -0.08
    æĪIJå°±æĦŁ
    -0.08
    éĤ£ç§į
    -0.08
    秽
    -0.08
    åķĨåĵģ
    -0.08
    POSITIVE LOGITS
    éĺ¡
    0.10
    Reality
    0.09
    天河
    0.09
    åij
    0.09
    arton
    0.09
    ä»·ä½į
    0.09
    esion
    0.09
    对å¾ħ
    0.08
     amount
    0.08
    hte
    0.08
    Activations Density 0.048%

    No Known Activations