© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 22045
    Prev
    Next
    INDEX
    Explanations

    full, depleted, virtually, different

    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
    åζæŃ¢
    -0.09
    úa
    -0.08
    _embedding
    -0.08
    é«ĺé¢Ŀ
    -0.08
    åĩ¤
    -0.08
    è±ķ
    -0.08
    ä½ĵçİ°åľ¨
    -0.08
    ä¸įæĿ¥
    -0.08
    é«ĺæĸ°åĮº
    -0.08
    å¿Į
    -0.08
    POSITIVE LOGITS
    æĢĢçĿĢ
    0.10
    æĶ¶èİ·
    0.10
    带çĿĢ
    0.10
    åIJĥè¿ĩ
    0.10
    gger
    0.10
    èµį
    0.10
    æľīä¿¡å¿ĥ
    0.09
    ered
    0.09
    åĶ¿
    0.09
    eled
    0.09
    Activations Density 0.084%

    No Known Activations