© 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. 22246
    Prev
    Next
    INDEX
    Explanations

    1990s years

    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
    åĴĮæĶ¯æĮģ
    -0.10
    èģ¿
    -0.09
    åīįä¸ĸ
    -0.09
    ä¾¥
    -0.09
    第ä¸Ģ书记
    -0.09
    åįĥåı¤
    -0.09
    pref
    -0.09
    å¾Īæĸ¹ä¾¿
    -0.09
    .sequence
    -0.08
    éģ´
    -0.08
    POSITIVE LOGITS
    nce
    0.09
    ingo
    0.08
    anz
    0.08
     Pager
    0.08
    rier
    0.08
    ×Ļת×Ķ
    0.08
    èıĮ
    0.08
    onne
    0.08
     Parcel
    0.08
    ersh
    0.08
    Activations Density 0.106%

    No Known Activations