© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9038
    Prev
    Next
    INDEX
    Explanations

    multiple-access systems

    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
    ä¿
    -0.09
    ãģĮãĤī
    -0.08
    EObject
    -0.08
    ×¢×ľ
    -0.08
    adir
    -0.08
    ìĨĶ
    -0.08
     ÑħоÑĤ
    -0.08
    å½ĵéĢī
    -0.08
    ç»ıåķĨ
    -0.08
    allis
    -0.08
    POSITIVE LOGITS
     pac
    0.11
    太平æ´ĭ
    0.10
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    æ¹¾
    0.09
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.09
     Pac
    0.08
    æ¶ħ
    0.08
    еÑģÑĤво
    0.08
     Vo
    0.08
     Bulls
    0.08
    Activations Density 0.050%

    No Known Activations