© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    pool or puddle

    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
    inal
    -0.10
    uzzi
    -0.09
    çĬ¯ç½ª
    -0.09
    æĺ§
    -0.08
    aceous
    -0.08
    社ä¼ļ责任
    -0.08
    lide
    -0.08
    çī©ä»·
    -0.08
     веÑīеÑģÑĤв
    -0.07
    åĿł
    -0.07
    POSITIVE LOGITS
    hips
    0.10
    æľīçĽĬ
    0.10
    spot
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.09
    ipped
    0.09
    åĬŁå¤«
    0.09
    å¾Īå°ı
    0.09
    è¯
    0.09
    uits
    0.09
    å¾Īæĥ³
    0.08
    Activations Density 0.004%

    No Known Activations