© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8160
    Prev
    Next
    INDEX
    Explanations

    quite a

    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
    æĽ´å¤ļçļĦæĺ¯
    -0.09
    æĽ´å¿«
    -0.08
    çļĦæľĢä½³
    -0.08
    æľĢ好
    -0.08
     ìķĦ주
    -0.08
    æģ°æģ°
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    nds
    -0.08
    æĽ´å¥½åľ°
    -0.08
    æĽ´å¤§
    -0.08
    POSITIVE LOGITS
    åı¯è§Ĥ
    0.11
    ä¸įéĶĻçļĦ
    0.10
    zelf
    0.10
    ucher
    0.10
    hei
    0.10
    竦
    0.09
    ened
    0.09
    iled
    0.09
    身åIJİ
    0.09
    HING
    0.09
    Activations Density 0.005%

    No Known Activations