© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30073
    Prev
    Next
    INDEX
    Explanations

    cost-benefit relationships

    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
    ä¸įæĥľ
    -0.11
    éĢłä»·
    -0.11
    erner
    -0.10
    éĩįåŀĭ
    -0.09
    以èĩ´
    -0.09
    åĵ¥
    -0.09
    çĭĻåĩ»
    -0.09
    ev
    -0.08
    æŀĭ
    -0.08
    .ev
    -0.08
    POSITIVE LOGITS
    æĬµ
    0.10
    ÑĮÑı
    0.09
    æį¢åıĸ
    0.08
    ä¼Ļ
    0.08
    éĻIJå®ļ
    0.08
    踮
    0.08
    åIJİæĤĶ
    0.08
    æī£éĻ¤
    0.08
     ÙħÙĤابÙĦ
    0.08
    emens
    0.08
    Activations Density 0.048%

    No Known Activations