© 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. 26648
    Prev
    Next
    INDEX
    Explanations

    investment and financial offerings

    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
    ukt
    -0.09
    涯
    -0.09
    æĥħæĻ¯
    -0.09
    ä½ľåĵģåĨħ容
    -0.08
    instr
    -0.08
    ä¸īåĽĽ
    -0.08
    éĺ¿å§¨
    -0.08
    éĺŁéķ¿
    -0.08
    uk
    -0.08
    inf
    -0.08
    POSITIVE LOGITS
    认è´Ń
    0.13
    ä¿ĿèįIJ
    0.13
    æĸ°èĤ¡
    0.12
    åıijè¡Į
    0.12
    çĶ³è´Ń
    0.11
    鸽
    0.10
    åĭŁéĽĨèµĦéĩij
    0.10
    æĭĽèĤ¡
    0.10
    åĭŁèµĦ
    0.09
    ç¨Ģ
    0.09
    Activations Density 0.024%

    No Known Activations