© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    endangered species extinction

    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
    åħī纤
    -0.09
    è£Ļ
    -0.09
    oogle
    -0.09
    ripp
    -0.09
     Themes
    -0.09
    enor
    -0.09
    èĢĥåľº
    -0.09
    ä¿ĺ
    -0.08
    å«ģ
    -0.08
    견
    -0.08
    POSITIVE LOGITS
    æ¿Ĵ
    0.16
    æ¿Ĵ临
    0.14
     extinction
    0.14
    çģŃ
    0.13
    çī©ç§į
    0.13
     endangered
    0.12
     extinct
    0.11
     species
    0.11
     endanger
    0.11
    å¿«è¦ģ
    0.10
    Activations Density 0.094%

    No Known Activations