© 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. 51489
    Prev
    Next
    INDEX
    Explanations

    let's get

    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
    èĹı
    -0.10
    èĢģ人家
    -0.09
    åĿĬ
    -0.09
    åıĭæĥħ
    -0.08
    æĪijå¾Ī
    -0.08
    è¿Ļ家ä¼Ļ
    -0.08
    颤
    -0.08
    å°±è¿Ļä¹Ī
    -0.08
    éĽªèĬ±
    -0.08
    çľĭä¸Ģçľĭ
    -0.08
    POSITIVE LOGITS
    ç¾İåѦ
    0.11
    ç¾İçļĦ
    0.10
     Rice
    0.10
    idor
    0.10
    并åıij
    0.09
    ãģķãģĪ
    0.09
    æĸŃè£Ĥ
    0.09
    æĸŃ
    0.09
     tote
    0.09
    ILLE
    0.09
    Activations Density 0.034%

    No Known Activations