© 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. 37053
    Prev
    Next
    INDEX
    Explanations

    designed with

    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
    ä½ĵéĩı
    -0.11
    鼶ç¢İ
    -0.10
    :`~
    -0.09
    èݲ
    -0.09
    _reports
    -0.09
    å®Īä½ı
    -0.09
     ÙĪاÙĦÙģ
    -0.09
    onde
    -0.09
    èĵ®
    -0.09
    奥æŀĹ
    -0.08
    POSITIVE LOGITS
    æ¦ľ
    0.09
     intent
    0.08
    è°Ĵ
    0.08
     greater
    0.08
    ieri
    0.08
    lette
    0.08
    åŁŃ
    0.08
    terra
    0.08
    lect
    0.08
    æķħæĦı
    0.08
    Activations Density 0.110%

    No Known Activations