© 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. 12967
    Prev
    Next
    INDEX
    Explanations

    given names

    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
    çī¹ä»·
    -0.22
    æĦĪ
    -0.20
    è¶Ĭ
    -0.19
    бÑĥ
    -0.19
     Habit
    -0.19
    elage
    -0.19
    æIJ¬è¿IJ
    -0.19
    ieux
    -0.19
    شر
    -0.18
    åıĸè¯ģ
    -0.18
    POSITIVE LOGITS
    让åŃ©åŃIJ
    0.23
    çĶ·åŃ©
    0.23
    çĪ¶æ¯į
    0.21
    åĦ¿åŃIJ
    0.20
    DIFF
    0.20
     names
    0.20
     son
    0.20
    Cy
    0.20
    æĹı
    0.20
     boy
    0.19
    Activations Density 0.019%

    No Known Activations