© 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. 51792
    Prev
    Next
    INDEX
    Explanations

    earnings, earn, earning

    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
     ÑģÑĤоим
    -0.11
    andi
    -0.10
    è¸Į
    -0.09
    edom
    -0.09
    æµģåĬ¨
    -0.08
    è¡Įèµ°
    -0.08
     Tigers
    -0.08
    åįłçĶ¨
    -0.08
    åįĩåѦ
    -0.08
    æīĭåĨĮ
    -0.08
    POSITIVE LOGITS
    odoxy
    0.10
    è·ijåİ»
    0.10
    éľħ
    0.10
    bow
    0.09
     rep
    0.09
    æ¦ľé¦ĸ
    0.09
    _nonce
    0.09
    azz
    0.09
    æİ¨è¿Ł
    0.09
    nings
    0.08
    Activations Density 0.032%

    No Known Activations