© 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. 35178
    Prev
    Next
    INDEX
    Explanations

    North America

    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
    å¢ĥåĨħ
    -0.11
    åĤĴ
    -0.10
    åĻľ
    -0.09
     dÄ±ÅŁÄ±
    -0.09
    oser
    -0.09
    igli
    -0.09
    gan
    -0.09
    naires
    -0.09
    为ä»Ģä¹Īä¼ļ
    -0.09
    éĺ¿æĭī
    -0.09
    POSITIVE LOGITS
    ÑĤал
    0.09
    lord
    0.08
    atu
    0.08
    ê¶Į
    0.08
    .social
    0.08
    ach
    0.08
    ç»Ĩèĩ´
    0.08
    akedown
    0.08
    á»ī
    0.08
    andin
    0.08
    Activations Density 0.032%

    No Known Activations