© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37905
    Prev
    Next
    INDEX
    Explanations

    revenue and tax deduction

    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
    åľ¨è¿Ļç§į
    -0.08
     sprink
    -0.08
    x
    -0.08
    éªĦ
    -0.08
     thừa
    -0.07
    åīįæľŁ
    -0.07
    æĻºåĬĽ
    -0.07
     Brighton
    -0.07
    ondon
    -0.07
    BO
    -0.07
    POSITIVE LOGITS
    奴
    0.10
     Curl
    0.10
    URN
    0.10
    è§ij
    0.09
    å¤Ħç½ļ
    0.09
    æŃ»èĢħ
    0.09
    -anchor
    0.09
    è¹´
    0.09
    åħ¥å¢ĥ
    0.09
    PILE
    0.09
    Activations Density 0.089%

    No Known Activations