© 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. 12566
    Prev
    Next
    INDEX
    Explanations

    suffix for 'transfer' or 'operation'

    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
    urf
    -0.19
    æĦı大
    -0.19
    ä»Ģä¹ĪåİŁåĽł
    -0.18
    unga
    -0.18
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.18
    åIJĦèĩªçļĦ
    -0.17
    rze
    -0.17
    庵
    -0.17
    ague
    -0.17
    大çĽĺ
    -0.17
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭ
    0.33
    åĨįåĪ°
    0.33
    åħ¨è¿ĩç¨ĭ
    0.30
    ä¸ĢæĿ¡é¾Ļ
    0.29
    è¿ĩç¨ĭ
    0.29
     phases
    0.28
     поÑĤом
    0.27
    ç´§æİ¥çĿĢ
    0.26
    åĩłæŃ¥
    0.26
     stages
    0.26
    Activations Density 0.494%

    No Known Activations