© 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. 11064
    Prev
    Next
    INDEX
    Explanations

    fossil recordpaleontology

    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
    elly
    -0.20
    ussy
    -0.19
    æĹĹ
    -0.19
    olson
    -0.19
     Cous
    -0.19
    antom
    -0.19
    oram
    -0.19
    æ¯ıèĤ¡
    -0.18
    OrDefault
    -0.18
    ucch
    -0.18
    POSITIVE LOGITS
    åĮĸçŁ³
    0.26
    åŁĭ
    0.24
     fossils
    0.23
    åĩºåľŁ
    0.22
    ç¢İçīĩ
    0.21
    齿
    0.21
    骸
    0.21
    骨骼
    0.21
    hor
    0.20
    å®Į好
    0.20
    Activations Density 0.013%

    No Known Activations