© 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. 20518
    Prev
    Next
    INDEX
    Explanations

    introducing names or definitions

    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
    RIES
    -0.09
     gol
    -0.09
    udge
    -0.09
    ieg
    -0.08
     Gol
    -0.08
    æħİéĩį
    -0.08
    éĻ¤æѤ
    -0.08
    mile
    -0.08
     Payne
    -0.08
    æĹ¢çĦ¶
    -0.08
    POSITIVE LOGITS
    称ä¹ĭ为
    0.19
    称为
    0.17
    åı«åģļ
    0.16
     called
    0.13
     Called
    0.12
    åı«
    0.12
    æĪijæĬĬ
    0.12
    åij¼åı«
    0.11
    Called
    0.11
    called
    0.11
    Activations Density 0.100%

    No Known Activations