© 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. 36278
    Prev
    Next
    INDEX
    Explanations

    median household income

    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
    éĶĻ
    -0.09
     Dancing
    -0.09
    ä»Ĺ
    -0.09
    .setDefault
    -0.09
    Uploaded
    -0.08
    leck
    -0.08
    å¹´åºķåīį
    -0.08
    箪
    -0.08
    éĮ¯
    -0.08
    berger
    -0.08
    POSITIVE LOGITS
    agem
    0.09
    å±ij
    0.09
    è¾ķ
    0.08
    åĨĽäºĭ
    0.08
     Bey
    0.08
    å¦į
    0.08
    éĢıæĺİ
    0.08
     bey
    0.08
    è§
    0.08
    æĥ¯
    0.08
    Activations Density 0.020%

    No Known Activations