© 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. 57726
    Prev
    Next
    INDEX
    Explanations

    cost reduction and savings

    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
    æīĪ
    -0.10
    æİĩ
    -0.10
    æľīæķĪåľ°
    -0.09
    ä¸ĩéĩĮ
    -0.08
    åĪ°å¤Ħ
    -0.08
    PUTE
    -0.08
    _scaled
    -0.08
    gün
    -0.08
    Ack
    -0.08
    ccione
    -0.08
    POSITIVE LOGITS
    æĪIJæľ¬
    0.10
    çļĦæĪIJæľ¬
    0.09
    APON
    0.09
    ä¸įéĢļ
    0.09
    饲åħ»
    0.09
    /proto
    0.09
    ãĤ³ãĤ¹ãĥĪ
    0.09
    æľªç»ıæİĪæĿĥ
    0.09
     costs
    0.09
    crate
    0.09
    Activations Density 0.042%

    No Known Activations