© 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. 6991
    Prev
    Next
    INDEX
    Explanations

    that's for sure

    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´½
    -0.10
    æĥ°
    -0.09
    ç²®
    -0.09
    nds
    -0.08
    å¾®å¦Ļ
    -0.08
     thoát
    -0.08
     handc
    -0.08
    acre
    -0.08
    åIJĮäºĭ们
    -0.08
    糧
    -0.08
    POSITIVE LOGITS
    èĤ¯å®ļ
    0.12
    没éĶĻ
    0.11
    à¹ģà¸Ļ
    0.11
    isse
    0.11
     sure
    0.11
    åĨį说
    0.10
    大å®Ĺ
    0.10
    è£ķ
    0.10
    毫æĹłçĸijéĹ®
    0.10
    æĹłçĸij
    0.09
    Activations Density 0.035%

    No Known Activations