© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51967
    Prev
    Next
    INDEX
    Explanations

    Hogan or Ajax, related to names and web requests

    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
    tle
    -0.10
    ingly
    -0.10
    é»ĺå¥ij
    -0.09
    ably
    -0.09
    è·»
    -0.08
    æĴij
    -0.08
    èIJ¥éĢłèī¯å¥½
    -0.08
    çī¢åĽºæłijç«ĭ
    -0.08
    æĴIJ
    -0.08
    åīįåIJİ
    -0.08
    POSITIVE LOGITS
    ../../../
    0.11
    arness
    0.11
    ging
    0.09
    çľ¼æ³ª
    0.09
    åįģ足
    0.09
    åĮĸçļĦ
    0.09
    以为
    0.09
    lte
    0.09
    ulous
    0.09
    otron
    0.09
    Activations Density 0.009%

    No Known Activations