© 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. 33620
    Prev
    Next
    INDEX
    Explanations

    spec or specification

    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
    oks
    -0.10
    ame
    -0.10
     lẽ
    -0.08
    -thirds
    -0.08
    wä
    -0.08
    cheduler
    -0.08
    æĴŀ
    -0.08
    ish
    -0.08
    wear
    -0.08
    å±ĢéĿ¢
    -0.08
    POSITIVE LOGITS
    acular
    0.11
    athing
    0.11
    å®ļäºĨ
    0.10
    imen
    0.10
    ол
    0.10
     hữu
    0.10
    igel
    0.10
    é«ĺãģĦ
    0.09
    åijĺ
    0.09
    ulative
    0.09
    Activations Density 0.038%

    No Known Activations