© 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. 53248
    Prev
    Next
    INDEX
    Explanations

    X between Y

    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
    enth
    -0.09
    è¿Ļ两
    -0.09
    æ´¹
    -0.09
    è¿Ļ两ç§į
    -0.09
    spe
    -0.09
    åĩºè½¨
    -0.09
    åĽłä¸ºå¥¹
    -0.09
    azer
    -0.09
    eneg
    -0.08
    eka
    -0.08
    POSITIVE LOGITS
    ç©¿éĢı
    0.10
    ricks
    0.10
    åIJĦ个
    0.10
    ä¸ĩåįĥ
    0.10
     relationships
    0.10
    åIJĦé¡¹å·¥ä½ľ
    0.10
    æİ£
    0.09
    åIJĦ
    0.09
    åIJĦ个çݯèĬĤ
    0.09
    relations
    0.09
    Activations Density 0.155%

    No Known Activations