© 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. 14554
    Prev
    Next
    INDEX
    Explanations

    accelerator laboratory staff

    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
     ÐŁÐ¾Ñĩем
    -0.22
    erot
    -0.22
    åī¯ä¸»å¸Ń
    -0.22
    åºĹéĵº
    -0.21
    ç»
    -0.21
    eward
    -0.19
    æĿµ
    -0.19
    ubar
    -0.19
    åĽ½æ°ijç»ıæµİ
    -0.18
     ÐĶмиÑĤÑĢ
    -0.18
    POSITIVE LOGITS
     Geb
    0.20
    çģµ
    0.19
    åİŁ
    0.18
    å§Ķ
    0.18
    æĥ¯
    0.18
    èĥ¸æĢĢ
    0.17
    åݲ
    0.17
     Pik
    0.17
     locator
    0.17
    è´§å¸ģ
    0.17
    Activations Density 0.005%

    No Known Activations