© 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. 62516
    Prev
    Next
    INDEX
    Explanations

    it's / it is / it has / it would

    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
    po
    -0.09
    éĥ½è®¤ä¸º
    -0.09
    å¤ļãģı
    -0.07
    认为
    -0.07
     spam
    -0.07
    аÑĤÑĥÑĢ
    -0.07
    å°±æĺ¯è¿Ļæł·
    -0.07
     liv
    -0.07
    就没æľī
    -0.07
    çļĦæīĢæľī
    -0.07
    POSITIVE LOGITS
    åıįæĺłäºĨ
    0.13
    ä½ĵçİ°äºĨ
    0.12
    ä¿ĥ使
    0.12
    åıijçĶŁåľ¨
    0.12
    çļĦåıijçĶŁ
    0.12
    åıįæĺłåĩº
    0.11
    azzi
    0.11
    uds
    0.11
    æłĩå¿ĹçĿĢ
    0.11
    æĦıåij³çĿĢ
    0.10
    Activations Density 0.169%

    No Known Activations