© 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. 36757
    Prev
    Next
    INDEX
    Explanations

    institution listed

    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
    社ä¼ļåĮĸ
    -0.12
    çĻĸ
    -0.10
    qualified
    -0.10
    _iface
    -0.09
    _Source
    -0.08
     liner
    -0.08
    æĬķå½±
    -0.08
    赶æĿ¥
    -0.08
    æĬ¥éģĵ
    -0.08
    çĸı导
    -0.08
    POSITIVE LOGITS
    ä¸ŃåİŁ
    0.10
    çĶ°éĩİ
    0.09
    ersen
    0.09
    ಡ
    0.09
    lew
    0.09
    å¯Ĩ
    0.09
     наÑĥÑĩ
    0.08
    伦çIJĨ
    0.08
    ç§ijçłĶ
    0.08
     Vanderbilt
    0.08
    Activations Density 0.074%

    No Known Activations