© 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. 16416
    Prev
    Next
    INDEX
    Explanations

    halftime breaks

    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
    沦
    -0.22
    åħ¥åѦ
    -0.22
    åĮ¹
    -0.20
    åħ¥åºĵ
    -0.19
    è¿İ
    -0.18
    oldem
    -0.18
    åĪĿåĪĽ
    -0.18
    ç±į
    -0.18
     Drive
    -0.18
    ç¼ł
    -0.18
    POSITIVE LOGITS
    ä¸ŃéĹ´
    0.38
    ä¸ŃéĢĶ
    0.35
     mid
    0.28
     intermediate
    0.28
     breaks
    0.25
    æľŁéĹ´
    0.25
    两次
    0.25
    mid
    0.24
    åīįåIJİ
    0.24
     intermedi
    0.23
    Activations Density 0.158%

    No Known Activations