© 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. 12021
    Prev
    Next
    INDEX
    Explanations

    shutter speed

    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
    åŃ£
    -0.23
    ç´¯
    -0.21
     Miles
    -0.20
     Mens
    -0.20
    habi
    -0.20
     McD
    -0.20
    ä¸įåIJĥ
    -0.19
    ellation
    -0.19
    åŃ£åIJİ
    -0.19
     Season
    -0.19
    POSITIVE LOGITS
    éĢŁåº¦
    0.21
    åįļè§Ī
    0.20
    æīĭåĬ¿
    0.20
    åĬ¨ä½ľ
    0.20
    çī¹æ´¾åijĺ
    0.20
    æŶéĹ´ä¸º
    0.20
    ä¸Ģæµģ
    0.19
     speed
    0.19
    åĬ¨æĦŁ
    0.19
    æįķæįī
    0.19
    Activations Density 0.003%

    No Known Activations