© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8789
    Prev
    Next
    INDEX
    Explanations

    lavender or pastebin.com links

    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
    же
    -0.09
    itt
    -0.09
    STER
    -0.09
    åĬĪ
    -0.08
    ött
    -0.08
    æ²Ľ
    -0.08
    arat
    -0.08
    NST
    -0.08
    esty
    -0.08
    ÑģÑĤав
    -0.08
    POSITIVE LOGITS
    çī¡
    0.10
    ktop
    0.10
    ëĬIJ
    0.10
    åıĸè¯ģ
    0.09
    ëĦ¤
    0.09
    ues
    0.09
    们éĥ½
    0.09
    åłĩ
    0.09
    ä¸Ģçīĩ
    0.09
    äºĪ
    0.08
    Activations Density 0.003%

    No Known Activations