© 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. 12042
    Prev
    Next
    INDEX
    Explanations

    number of years

    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
     коллекÑĤив
    -0.09
    éĴ¤
    -0.08
    åĹ£
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    ä¸įéĻIJ
    -0.08
    å¼ĢéŨ
    -0.08
    åīįæīĢ
    -0.08
    宪
    -0.08
    äºĨ大éĩıçļĦ
    -0.08
    éĢ¢
    -0.08
    POSITIVE LOGITS
    æľ¬ç«Ļ
    0.09
    asser
    0.09
    /ext
    0.09
    IDL
    0.09
     Dresses
    0.08
    edly
    0.08
    reed
    0.08
    èĬĬ
    0.08
    NodeType
    0.08
    åij¨äºĶ
    0.08
    Activations Density 0.004%

    No Known Activations