© 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. 47865
    Prev
    Next
    INDEX
    Explanations

    size and scale

    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
    æ£Ģ
    -0.09
    .pad
    -0.09
    ides
    -0.09
    æ¸Ń
    -0.08
    æĽ·
    -0.08
     Ivanka
    -0.08
    ä¸ŃæľŁ
    -0.08
    座
    -0.08
    æľĢå¤ļ
    -0.08
     ÑĤÑĭÑģÑı
    -0.08
    POSITIVE LOGITS
    è§Ħ模
    0.14
    ä½ĵéĩı
    0.14
    ä½ĵ积
    0.14
    年纪
    0.12
    è¦ı模
    0.12
     size
    0.11
    åºŀ大çļĦ
    0.11
     khá»iji
    0.11
    éĩįéĩı
    0.11
    èĬ
    0.11
    Activations Density 0.145%

    No Known Activations