© 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. 50150
    Prev
    Next
    INDEX
    Explanations

    the following phrases

    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
    åijĬ
    -0.11
    æİ¥è¿ij
    -0.09
    以èī²
    -0.08
    çĶµä¿¡
    -0.08
    åĢļ
    -0.08
    xing
    -0.08
    ucch
    -0.08
     Mature
    -0.08
    åħħ足çļĦ
    -0.08
    itte
    -0.08
    POSITIVE LOGITS
    ä¸ĩéĩĮ
    0.09
    alty
    0.09
    å¸Ń
    0.09
    çİ«çij°
    0.09
    åģĮ
    0.09
    ä¸ĩæĪ·
    0.09
    èĨĬ
    0.09
    寻常
    0.09
    èĬĻèĵī
    0.09
    ãģ¬
    0.09
    Activations Density 0.043%

    No Known Activations