© 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. 10632
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    解åĨ³éĹ®é¢ĺ
    -0.11
    arde
    -0.10
    æĬĬä»ĸ
    -0.10
    å¿ĥçIJĨåѦ
    -0.10
    æĬĬæīĭ
    -0.09
    è¾ĩ
    -0.09
    ç¡®ä¿Ŀ
    -0.09
    çķ¢
    -0.09
    æ¯ķ
    -0.09
    ç¿Ł
    -0.09
    POSITIVE LOGITS
    建设åĴĮ
    0.10
     boot
    0.09
    å°±è¿Ļæł·
    0.09
    å°±è¿Ļä¹Ī
    0.09
    è§ĤæľĽ
    0.08
    éī
    0.08
    .Requires
    0.08
    å¤ļãģı
    0.08
    omers
    0.08
    .getAs
    0.08
    Activations Density 0.040%

    No Known Activations