© 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. 39373
    Prev
    Next
    INDEX
    Explanations

    Apache Hadoop

    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
    amac
    -0.09
     Pew
    -0.09
    å¹²äºĭ
    -0.09
    æݥ管
    -0.09
     Та
    -0.09
    æĥij
    -0.09
    è¿İ
    -0.08
    åģļä¸Ģ个
    -0.08
    æį¢åıĸ
    -0.08
     нев
    -0.08
    POSITIVE LOGITS
    Apache
    0.11
     hoodie
    0.10
    åijĬ
    0.10
    éĽī
    0.10
    apache
    0.10
    é£ŀè¡Į
    0.09
    触
    0.09
    .apache
    0.09
    丼æŀĹ
    0.09
    鸯
    0.09
    Activations Density 0.303%

    No Known Activations