© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27955
    Prev
    Next
    INDEX
    Explanations

    kidding or serious

    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
    st
    -0.10
    奴
    -0.10
     dissip
    -0.09
    ÑıÑģ
    -0.08
     prer
    -0.08
    wiÄħ
    -0.08
     laure
    -0.08
    anel
    -0.08
    çī¢
    -0.08
    çķĮçļĦ
    -0.08
    POSITIVE LOGITS
    æĸ«
    0.10
    åĭĥåĭĥ
    0.09
    大家åĪĨ享
    0.09
    æĢ§å¼º
    0.08
    imon
    0.08
    éĥ¨åĪĨåĨħ容
    0.08
    å²·
    0.08
    icum
    0.08
    fen
    0.08
     Bout
    0.08
    Activations Density 0.003%

    No Known Activations