© 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. 9036
    Prev
    Next
    INDEX
    Explanations

    aid or rescue

    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
    éĹ»è¨Ģ
    -0.10
    éĻĦåĬł
    -0.09
    çĥĪ
    -0.09
    tti
    -0.09
    ä¸ĩ象
    -0.09
    ument
    -0.09
    å¯Ħæīĺ
    -0.08
    åĽŀ头çľĭ
    -0.08
    gart
    -0.08
    ellig
    -0.08
    POSITIVE LOGITS
    æĹĭ
    0.10
     aid
    0.10
    æı´åĬ©
    0.09
    æķij
    0.09
    åħĭ
    0.09
    缸åĬ©
    0.09
    èĹķ
    0.09
    帮å¿Ļ
    0.09
     pits
    0.08
    åı·
    0.08
    Activations Density 0.027%

    No Known Activations