© 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. 8792
    Prev
    Next
    INDEX
    Explanations

    sought-after

    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
    Manifest
    -0.10
    对éĿ¢
    -0.09
    alls
    -0.08
    Fold
    -0.08
    å¾Īéĩįè¦ģ
    -0.08
     matter
    -0.08
    衬
    -0.08
    ÐĽÐ¬
    -0.08
     mattered
    -0.08
    æ³£
    -0.08
    POSITIVE LOGITS
    ospace
    0.09
    å·²ä¹ħçļĦ
    0.09
    ickle
    0.09
    _mapper
    0.09
    åĿ¯
    0.09
    ulous
    0.09
    é³Į
    0.09
    ATAR
    0.09
    ä¹ĭåĬ¿
    0.09
    çŀij
    0.08
    Activations Density 0.014%

    No Known Activations