© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    earning a living, making money

    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
     пÑĢоÑĤ
    -0.12
    马ä¸ģ
    -0.11
    NSNotification
    -0.10
    æľīä¸Ģä½į
    -0.10
    å°ı康
    -0.10
    âĸ»
    -0.10
    衽
    -0.09
     PROT
    -0.09
    赪
    -0.09
    åŁ
    -0.09
    POSITIVE LOGITS
    plex
    0.08
    fully
    0.08
    ä½ĵ系建设
    0.08
    byn
    0.08
    obe
    0.07
    è°£
    0.07
    èģĶ
    0.07
    ä¸įå¤ļ
    0.07
    .StringUtils
    0.07
    F
    0.07
    Activations Density 0.014%

    No Known Activations