© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    waiting or expecting

    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
    мÑı
    -0.09
    mdat
    -0.08
    æľ¬ç½ij
    -0.08
    apan
    -0.08
    æı½
    -0.08
    æľīåºı
    -0.07
    æĹ¥æĬ¥
    -0.07
    â¬ĩ
    -0.07
    å¹ħ
    -0.07
    .air
    -0.07
    POSITIVE LOGITS
    çĵ£
    0.10
    åºķ线
    0.09
     ÄIJo
    0.09
    iston
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    okit
    0.09
    åķľ
    0.09
    娱
    0.09
    æ·ĸ
    0.09
    entlich
    0.09
    Activations Density 0.010%

    No Known Activations