© 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. 38091
    Prev
    Next
    INDEX
    Explanations

    algal blooms

    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
    æݧ
    -0.11
     NR
    -0.09
    ARS
    -0.08
    NE
    -0.08
     organ
    -0.08
    ä¸įåĪ°
    -0.08
    ennes
    -0.08
    æĶ¶åıĹ
    -0.08
    aston
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    POSITIVE LOGITS
    æ¥ŀ
    0.10
    åĩłä½ķ
    0.09
    çĻŀ
    0.09
    çĴĩ
    0.09
     Cald
    0.09
    uras
    0.09
    绣
    0.09
    浪
    0.09
    .EVT
    0.08
    å®£ä¼łæ´»åĬ¨
    0.08
    Activations Density 0.171%

    No Known Activations