© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12318
    Prev
    Next
    INDEX
    Explanations

    place name suffixes

    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
    Cities
    -0.25
    è£Ĩ
    -0.20
    _fu
    -0.20
    æĮĤåľ¨
    -0.19
    Fu
    -0.19
    åĨĻåŃĹ楼
    -0.18
    åįĸåľº
    -0.18
    cities
    -0.18
    大åŁİå¸Ĥ
    -0.18
     Affero
    -0.18
    POSITIVE LOGITS
    å°ıåѦ
    0.25
     village
    0.24
    æĿijæĿijæ°ij
    0.24
    æĿijæ°ij
    0.23
    æĿijåŃIJ
    0.21
    åĨľåľº
    0.20
    æĿij
    0.20
    åĨľæ°ij
    0.20
    乡æĿij
    0.20
    è¿Ļ个åIJįåŃĹ
    0.19
    Activations Density 0.251%

    No Known Activations