© 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. 9070
    Prev
    Next
    INDEX
    Explanations

    rocket engines and space travel

    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
    sst
    -0.09
    lessly
    -0.09
    loom
    -0.09
    ities
    -0.09
    abled
    -0.09
    åŁºè°ĥ
    -0.09
    大å±Ģ
    -0.09
    ir
    -0.09
    æĪĺçķ¥
    -0.08
     kiá»ĩn
    -0.08
    POSITIVE LOGITS
    eer
    0.12
    çĦ¶æĺ¯
    0.12
    strap
    0.11
    iled
    0.11
    anium
    0.11
    ting
    0.10
    itus
    0.10
    IGHT
    0.10
    bird
    0.10
    itude
    0.09
    Activations Density 0.006%

    No Known Activations