© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47702
    Prev
    Next
    INDEX
    Explanations

    venture capital and funding rounds

    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
    ä¸ĩ个
    -0.08
    ب
    -0.08
    éĻĢ
    -0.08
    ä½ıæīĢ
    -0.08
    umont
    -0.08
    诸èijĽäº®
    -0.08
    è¯Ĩ
    -0.08
    ä¹ĭæĥħ
    -0.08
    çīĪæĿĥå½Ĵ
    -0.08
    éĬ®
    -0.08
    POSITIVE LOGITS
    æĪ´
    0.10
    zem
    0.09
    æ¢Ń
    0.09
    ä¸Ģæ³¢
    0.09
    èµĶ
    0.09
    ERA
    0.09
    dle
    0.08
    åµ´
    0.08
    é¾Ł
    0.08
    ÑĢоÑĪ
    0.08
    Activations Density 0.023%

    No Known Activations