© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6932
    Prev
    Next
    INDEX
    Explanations

    would have/be

    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
    鸬
    -0.09
    æĬ¢åįł
    -0.09
    æĬ¢
    -0.09
    otes
    -0.09
    ables
    -0.09
    ened
    -0.08
    à¹Ħว
    -0.08
    赡
    -0.08
     sake
    -0.08
     vit
    -0.08
    POSITIVE LOGITS
    èĩªæĿ¥
    0.10
    丰åİļ
    0.10
    å¦Ĥæľī
    0.10
    ç½Ħ
    0.10
    ìŀ¥ìĿĦ
    0.09
    æİĪäºĪ
    0.09
     Powerful
    0.09
    ALAR
    0.09
    ä¸į足以
    0.09
    è´½
    0.09
    Activations Density 0.041%

    No Known Activations