© 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. 20773
    Prev
    Next
    INDEX
    Explanations

    prints and art sizes

    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
    åIJĮæľŁ
    -0.09
    ammer
    -0.08
    绸
    -0.08
    éĤ£åıª
    -0.08
    quate
    -0.08
    縳
    -0.08
    积æŀģä½ľçĶ¨
    -0.08
    à¸Ĺย
    -0.08
    天æīį
    -0.08
     sculpt
    -0.08
    POSITIVE LOGITS
    è¾ĥå·®
    0.09
    ç¯Ħ
    0.08
    åºĩ
    0.08
    çİ°è´§
    0.08
    çŀŃ
    0.08
    ä¸ĵ享
    0.08
    æĬ¤åį«
    0.08
    èĮĥåĽ´åĨħ
    0.08
    mpr
    0.08
     Lac
    0.08
    Activations Density 0.031%

    No Known Activations