© 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. 15465
    Prev
    Next
    INDEX
    Explanations

    endemic species or unique creatures

    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
    -vars
    -0.22
    estone
    -0.21
    ç©°
    -0.21
    åľºä¸Ĭ
    -0.21
     @[
    -0.20
    表彰
    -0.20
    ä¸Ģæľµ
    -0.19
    /raw
    -0.19
    åĨ³
    -0.19
    schlä
    -0.19
    POSITIVE LOGITS
    çĭ¬çī¹
    0.28
    unique
    0.28
    çĭ¬çī¹çļĦ
    0.27
     unique
    0.24
    çĭ¬ä¸ĢæĹłäºĮ
    0.24
    (unique
    0.24
     uniqueness
    0.23
     Ñĥника
    0.23
     uniquely
    0.23
    Catch
    0.23
    Activations Density 0.110%

    No Known Activations