© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13581
    Prev
    Next
    INDEX
    Explanations

    wildlife habitat protection and nature reserves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Basement
    -0.21
    arez
    -0.21
    ourg
    -0.20
    éľĸ
    -0.20
    渥
    -0.19
    izr
    -0.19
    rico
    -0.19
    ä¸Ģç¬ij
    -0.18
    arat
    -0.18
    å·´æĭī
    -0.18
    POSITIVE LOGITS
    éĩİçĶŁåĬ¨çī©
    0.39
     wildlife
    0.37
     habitat
    0.35
    çī©ç§į
    0.34
    鸣类
    0.33
     bird
    0.32
    çĶŁæĢģ
    0.31
     species
    0.31
     biodiversity
    0.30
    æłĸ
    0.29
    Activations Density 0.154%

    No Known Activations