© 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. 33801
    Prev
    Next
    INDEX
    Explanations

    limited few

    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
    åģ¥åº·çļĦ
    -0.10
    身ä½ĵåģ¥åº·
    -0.10
    羣å®ŀçļĦ
    -0.09
    å°½åĬĽ
    -0.09
    以人为
    -0.09
    åIJİæŀľ
    -0.09
    æ±Ń
    -0.09
    åŃĶåŃIJ
    -0.09
    åĿĩçĶ±
    -0.09
    æĴ°
    -0.09
    POSITIVE LOGITS
    å°ijæķ°
    0.25
     few
    0.25
    ä¸įå¤ļ
    0.21
    few
    0.20
    Few
    0.19
     Few
    0.19
    åĩłä¸ª
    0.18
    åĩłå®¶
    0.18
    å¾Īå°ij
    0.18
    åĩłä¸ªäºº
    0.17
    Activations Density 0.093%

    No Known Activations