© 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. 16450
    Prev
    Next
    INDEX
    Explanations

    newsweek, education week, adweek, entertainment weekly

    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
    ä¸ĩæĪ·
    -0.21
    Vir
    -0.19
    uchen
    -0.19
    esti
    -0.19
    åħijçİ°
    -0.19
    رش
    -0.18
    éľı
    -0.18
    à¹ģห
    -0.18
    æĩĪ
    -0.18
    Focused
    -0.18
    POSITIVE LOGITS
     jog
    0.20
    çĽ²
    0.19
    /--
    0.18
     Toro
    0.18
    Accuracy
    0.18
    oids
    0.18
    cepts
    0.17
     lạc
    0.17
    itecture
    0.17
     strconv
    0.17
    Activations Density 0.001%

    No Known Activations