© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12597
    Prev
    Next
    INDEX
    Explanations

    compliance, frequency, visiting, riders, support

    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
    éĢłç¦ı
    -0.18
    slack
    -0.18
    å®Įæķ´æĢ§
    -0.18
    å½Ĺ
    -0.18
    客æłĪ
    -0.18
    _ACC
    -0.18
    çĭĪ
    -0.17
    åĽ½æĥħ
    -0.17
    OFF
    -0.17
    /twitter
    -0.17
    POSITIVE LOGITS
    æĦ¿æĦı
    0.23
    æİı
    0.22
    èĤ¯
    0.22
    ä¸ºçĽ®æłĩ
    0.20
    ommen
    0.20
    è¿ĽæĿ¥
    0.20
    ä¸įèĩ³äºİ
    0.20
    æľīæĽ´å¥½çļĦ
    0.19
    主åĬ¨
    0.19
    è·Łä½ł
    0.19
    Activations Density 0.059%

    No Known Activations