© 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. 8487
    Prev
    Next
    INDEX
    Explanations

    's + noun/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
    æĿ³
    -0.09
    ä¸Ģé¡¿
    -0.09
    åŁ
    -0.09
    æĪIJéķ¿ä¸º
    -0.09
    onis
    -0.08
    客æĪ·æľįåĬ¡
    -0.08
    ew
    -0.08
    ле
    -0.08
    kle
    -0.08
    æĢĻ
    -0.08
    POSITIVE LOGITS
    è¶Ĭ
    0.10
    chrift
    0.09
    ras
    0.09
    æ²IJæµ´
    0.09
    è¶Ĭé«ĺ
    0.09
    å°±æĺ¯è¿Ļæł·
    0.09
    otropic
    0.09
    æķĪçĽĬ
    0.09
    ainen
    0.09
    æ¿ĢåĬ¨
    0.09
    Activations Density 0.067%

    No Known Activations