© 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. 48565
    Prev
    Next
    INDEX
    Explanations

    funded by or from

    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
    aldo
    -0.09
    ç½ijéĢļ
    -0.08
    obel
    -0.08
    aim
    -0.08
     SHARES
    -0.08
    rego
    -0.08
    æĦŁåıĹ
    -0.08
     IMPLIED
    -0.08
    èĢĨ
    -0.08
    åģĩ
    -0.08
    POSITIVE LOGITS
    éĤªæģ¶
    0.09
    èĩªèº«çļĦ
    0.09
    æĢ¨
    0.09
    ä¸į平衡
    0.09
    itable
    0.09
    å¾Ĺèµ·
    0.09
    åĪĩéĻ¤
    0.09
    åIJĦçķĮ
    0.08
    æIJ¬
    0.08
     cliente
    0.08
    Activations Density 0.036%

    No Known Activations