© 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. 30200
    Prev
    Next
    INDEX
    Explanations

    tax deductions and returns

    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
     financier
    -0.10
    åĬŁè¯¾
    -0.09
    è¯Ńæ°Ķ
    -0.09
    é«ĺå°Ķ
    -0.09
    èĩªçĶ±è´¸æĺĵ
    -0.08
    æĶĢ
    -0.08
    ä¸ĩ人
    -0.08
    åĴĮå¹³
    -0.08
    绿è±Ĩ
    -0.08
     Burg
    -0.08
    POSITIVE LOGITS
    æī£éĻ¤
    0.12
    chin
    0.10
    åĪĨæĪIJ
    0.10
    æ±Ĺ
    0.10
    足
    0.10
    éľĩ
    0.10
    èĩªåĬ¨
    0.10
    éĥ½è®¤ä¸º
    0.09
     deduction
    0.09
    离èģĮ
    0.09
    Activations Density 0.034%

    No Known Activations